Linear filtering for noise-suppressed speech detection

Description

FIELD OF THE DISCLOSURE

The disclosure is related to consumer goods and, more particularly, to methods, systems, products, features, services, and other elements directed to media playback and aspects thereof.

BACKGROUND

Options for accessing and listening to digital audio in an out-loud setting were limited until in 2003, when Sonos, Inc. filed for one of its first patent applications, entitled “Method for Synchronizing Audio Playback between Multiple Network devices,” and began offering a media playback system for sale in 2005. The Sonos Wireless HiFi System enables people to experience music from many sources via one or more networked playback devices. Through a software control application installed on a smartphone, tablet, or computer, one can play what he or she wants in any room that has a networked playback device. Additionally, using the controller, for example, different songs can be streamed to each room with a playback device, rooms can be grouped together for synchronous playback, or the same song can be heard in all rooms synchronously.

Given the ever-growing interest in digital media, there continues to be a need to develop consumer-accessible technologies to further enhance the listening experience.

SUMMARY

The present disclosure describes systems and methods for, among other things, processing audio content captured by multiple networked microphones in order to suppress noise content from the captured audio and detect a voice input in the captured audio.

Some example embodiments involve capturing, via a plurality of microphones of a network device, (i) a first audio signal via a first microphone of the plurality of microphones and (ii) a second audio signal via a second microphone of the plurality of microphones. The first audio signal comprises first noise content from a noise source and the second audio signal comprises second noise content from the same noise source. The network device identifies the first noise content in the first audio signal and uses the identified first noise content to determine an estimated noise content captured by the plurality of microphones. Then the network device uses the estimated noise content to suppress the first noise content in the first audio signal and the second noise content in the second audio signal. The network device combines the suppressed first audio signal and the suppressed second audio signal into a third audio signal. Finally, the network device determines that the third audio signal includes a voice input comprising a wake word and, in response to the determination, transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word.

Some embodiments include an article of manufacture comprising tangible, non-transitory, computer-readable media storing program instructions that, upon execution by one or more processors of a network device, cause the network device to perform operations in accordance with the example embodiments disclosed herein.

Some embodiments include a network device comprising one or more processors, as well as tangible, non-transitory, computer-readable media storing program instructions that, upon execution by the one or more processors, cause the network device to perform operations in accordance with the example embodiments disclosed herein.

This summary overview is illustrative only and is not intended to be limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the figures and the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

Features, aspects, and advantages of the presently disclosed technology may be better understood with regard to the following description, appended claims, and accompanying drawings where:

FIG. 1 shows an example media playback system configuration in which certain embodiments may be practiced;

FIG. 2 shows a functional block diagram of an example playback device;

FIG. 3 shows a functional block diagram of an example control device;

FIG. 4 shows an example controller interface;

FIG. 5 shows an example plurality of network devices;

FIG. 6 shows a functional block diagram of an example network microphone device;

FIG. 7A shows an example network device having microphones arranged in a beamforming array according to some embodiments.

FIG. 7B shows an example network device having microphones arranged in a disarrayed fashion according to some embodiments.

FIG. 7C shows two example network devices having microphones arranged across both devices, according to some embodiments.

FIG. 8 shows an example network configuration in which certain embodiments may be practiced.

FIG. 9 shown an example method according to some embodiments.

FIG. 10 shows an example voice input according to some embodiments.

FIG. 11 shows experimental results of wake word detection improvement over a static beamforming technique.

The drawings are for the purpose of illustrating example embodiments, but it is understood that the inventions are not limited to the arrangements and instrumentalities shown in the drawings.

DETAILED DESCRIPTION
I. Overview

The present disclosure describes systems and methods for, among other things, performing noise suppression using networked microphones. In some embodiments, one or more microphones of the microphone network is a component of a network device, such as a voice-enabled device (“VED”). In operation, a VED (or other network device) equipped with a microphone listens for a “wake word” or wake phrase that prompts the VED to capture speech for voice command processing. In some embodiments, a wake phrase includes a wake word, or vice-versa.

Some examples of a “wake word” (or wake phrase) may include, “Hey Sonos” for a Sonos VED, “Alexa” for an Amazon VED, or “Siri” for an Apple VED. Other VEDs from other manufacturers may use different wake words and/or phrases. In operation, a VED equipped with a microphone listens for its wake word. And in response to detecting its wake word, the VED (individually or in combination with one or more other computing devices) records speech following the wake word, analyzes the recorded speech to determine a voice command, and then implements the voice command. Examples of typical voice commands include, “Play my Beatles playlist,” “Turn on my living room lights,” “Set my thermostat to 75 degrees,” “add milk and bananas to my shopping list,” and so on.

FIG. 10 shows an example of a voice input 1090 that can be provided to a VED. The voice input 1090 may comprise a wake word 1092, a voice utterance 1094, or both. The voice utterance portion 1094 may include, for example, one or more spoken commands 1096 (identified individually as a first command 1096a and a second command 1096b) and one or more spoken keywords 1098 (identified individually as a first keyword 1098a and a second keyword 1098b). In one example, the first command 1096a can be a command to play music, such as a specific song, album, playlist, etc. In this example, the keywords 1098 may be one or more words identifying one or more zones in which the music is to be played, such as the Living Room and the Dining Room shown in FIG. 1. In some examples, the voice utterance portion 1094 can include other information, such as detected pauses (e.g., periods of non-speech) between words spoken by a user, as shown in FIG. 10. The pauses may demarcate the locations of separate commands, keywords, or other information spoken by the user within the voice utterance portion 1094.

As further shown in FIG. 10, the VED may direct a playback device to temporarily reduce the amplitude of (or “duck”) audio content playback during capture of a wake word and/or a voice utterance 1096 comprising a command. Ducking can reduce audio interference and improve voice processing accuracy. Various examples of wake words, voice commands, and related voice input capture techniques, processing, devices, and systems, can be found, for example, in U.S. patent application Ser. No. 15/721,141, filed Sep. 27, 2017 and entitled “Media Playback System with Voice Assistance,” which is incorporated herein by reference in its entirety.

One challenge with determining voice commands is obtaining a high-quality recording of the speech comprising the voice command for analysis. A higher quality recording of the speech comprising a voice command is easier for voice algorithms to analyze as compared to a lower quality recording of the speech comprising the voice command. Obtaining a high-quality recording of speech comprising a voice command can be challenging in environments where multiple people may be talking, appliances (e.g., televisions, stereos, air conditioners, dishwashers, etc.) are making noise, and other extraneous sounds are present.

One way to improve the quality of sound recordings comprising voice commands is to employ a microphone array and use beamforming to (i) amplify sound coming from the direction from where the speech containing the voice command originated relative to the microphone array and (ii) attenuate sound coming from other directions relative to the microphone array. In beamforming systems, a plurality of microphones arranged in a structured array can perform spatial localization of sounds (i.e., determine the direction from where a sound originated) relative to the microphone array. However, while effective for suppressing unwanted noise from sound recordings, beamforming has limitations. For example, because beamforming requires microphones to be arranged in a particular array configuration, beamforming is feasible only in scenarios in which it is possible to implement such an array of microphones. Some network devices may not be capable of supporting such an array of microphones due to hardware or other design constraints. As described in greater detail below, network devices and associated systems and methods configured in accordance with the various embodiments of the technology can address these and other challenges associated with conventional techniques, such as traditional beamforming, for suppressing noise content from captured audio.

The present disclosure describes using multi-microphone noise suppression techniques that do not necessarily rely on the geometrical arrangement of the microphones. Rather, techniques for suppressing noise in accordance with various embodiments involve linear time-invariant filtering of an observed noisy process, assuming known stationary signal and noise spectra, and additive noise. In some embodiments, present techniques use first audio content captured by one or more respective microphones within a network of microphones to estimate noise in second audio content that is concurrently being captured by one or more other respective microphones of the microphone network. The estimated noise from the first audio content can then be used to filter out noise and preserve speech in the second audio content.

In various embodiments, present techniques may involve aspects of Wiener filtering. Traditional Wiener filtering techniques have been used in image filtering and noise cancelling, but often comprise fidelity of the resultant filtered signal. The inventors have recognized, however, that Wiener-filtering-based and related techniques can be applied to voice input detection (e.g., wake word detection) in a way that enhances voice detection accuracy compared to voice input detection using traditional beam forming techniques.

In some embodiments, a microphone network implementing multi-microphone noise suppression techniques of the various embodiments is a component of a network device. A network device is any computing device comprising (i) one or more processors, (ii) one or more network interfaces and/or one or more other types of communication interfaces, and (iii) tangible, non-transitory computer-readable media comprising instructions encoded therein, where the instructions, when executed at least in part by the one or more processors, cause the network device to perform the functions disclosed and described herein. A network device is generic class of devices that includes, but is not limited to voice enabled devices (VEDs), networked microphone devices (NMDs), audio playback devices (PBDs), and video playback devices (VPDs). VEDs are a class of devices that includes but is not limited to NMDs, PBDs, and VPDs. For example, one type of VED is an NMD, which is a network device comprising one or more processors, a network interface, and one or more microphones. Some NMDs may additionally include one or more speakers and perform media playback functions. Another type of VED is a PBD, which is a network device comprising one or more processors, a network interface, and one or more speakers. Some PBDs may optionally include one or more microphones and perform the functions of an NMD. Yet another type of VED is a VPD, which is a network device comprising one or more processors, a network interface, one or more speakers, and at least one video display. Some VPDs may optionally include one or more microphones and perform the functions of an NMD. PBDs and VPDs may be generally referred to as media playback devices.

Each of the above-described VEDs may implement at least some voice control functionality, which allows the VED (individually or perhaps in combination with one or more other computing devices) to act upon voice commands received via its microphones, thereby allowing a user to control the VED and perhaps other devices, too.

Further embodiments include tangible, non-transitory computer-readable media having stored thereon program instructions that, upon execution by a computing device, cause the computing device to perform the features and functions disclosed and described herein.

Some embodiments include a computing device comprising at least one processor, as well as data storage and program instructions. In operation, the program instructions are stored in the data storage, and upon execution by the at least one processor, cause the computing device (individually or in combination with other components or systems) to perform the features and functions disclosed and described herein.

While some examples described herein may refer to functions performed by given actors such as “users” and/or other entities, it should be understood that this is for purposes of explanation only. The claims should not be interpreted to require action by any such example actor unless explicitly required by the language of the claims themselves. It will be understood by one of ordinary skill in the art that this disclosure includes numerous other embodiments.

II. Example Operating Environment

FIG. 1 shows an example configuration of a media playback system 100 in which one or more embodiments disclosed herein may be practiced or implemented. The media playback system 100 as shown is associated with an example home environment having several rooms and spaces, such as for example, a master bedroom, an office, a dining room, and a living room. As shown in the example of FIG. 1, the media playback system 100 includes playback devices 102-124, control devices 126 and 128, and a wired or wireless network router 130. In operation, any of the playback devices (PBDs) 102-124 may be voice-enabled devices (VEDs) as described earlier.

Further discussions relating to the different components of the example media playback system 100 and how the different components may interact to provide a user with a media experience may be found in the following sections. While discussions herein may generally refer to the example media playback system 100, technologies described herein are not limited to applications within, among other things, the home environment as shown in FIG. 1. For instance, the technologies described herein may be useful in environments where multi-zone audio may be desired, such as, for example, a commercial setting like a restaurant, mall or airport, a vehicle like a sports utility vehicle (SUV), bus or car, a ship or boat, an airplane, and so on.

a. Example Playback Devices

FIG. 2 shows a functional block diagram of an example playback device 200 that may be configured to be one or more of the playback devices 102-124 of the media playback system 100 of FIG. 1. As described above, a playback device (PBD) 200 is one type of voice-enabled device (VED).

The playback device 200 includes one or more processors 202, software components 204, memory 206, audio processing components 208, audio amplifier(s) 210, speaker(s) 212, a network interface 214 including wireless interface(s) 216 and wired interface(s) 218, and microphone(s) 220. In one case, the playback device 200 may not include the speaker(s) 212, but rather a speaker interface for connecting the playback device 200 to external speakers. In another case, the playback device 200 may include neither the speaker(s) 212 nor the audio amplifier(s) 210, but rather an audio interface for connecting the playback device 200 to an external audio amplifier or audio-visual receiver.

In some examples, the one or more processors 202 include one or more clock-driven computing components configured to process input data according to instructions stored in the memory 206. The memory 206 may be a tangible, non-transitory computer-readable medium configured to store instructions executable by the one or more processors 202. For instance, the memory 206 may be data storage that can be loaded with one or more of the software components 204 executable by the one or more processors 202 to achieve certain functions. In one example, the functions may involve the playback device 200 retrieving audio data from an audio source or another playback device. In another example, the functions may involve the playback device 200 sending audio data to another device or playback device on a network. In yet another example, the functions may involve pairing of the playback device 200 with one or more playback devices to create a multi-channel audio environment.

Certain functions may involve the playback device 200 synchronizing playback of audio content with one or more other playback devices. During synchronous playback, a listener will preferably not be able to perceive time-delay differences between playback of the audio content by the playback device 200 and the one or more other playback devices. U.S. Pat. No. 8,234,395 entitled, “System and method for synchronizing operations among a plurality of independently clocked digital data processing devices,” which is hereby incorporated by reference, provides in more detail some examples for audio playback synchronization among playback devices.

The memory 206 may further be configured to store data associated with the playback device 200, such as one or more zones and/or zone groups the playback device 200 is a part of, audio sources accessible by the playback device 200, or a playback queue that the playback device 200 (or some other playback device) may be associated with. The data may be stored as one or more state variables that are periodically updated and used to describe the state of the playback device 200. The memory 206 may also include the data associated with the state of the other devices of the media system, and shared from time to time among the devices so that one or more of the devices have the most recent data associated with the system. Other embodiments are also possible.

The audio processing components 208 may include one or more digital-to-analog converters (DAC), an audio preprocessing component, an audio enhancement component or a digital signal processor (DSP), and so on. In one embodiment, one or more of the audio processing components 208 may be a subcomponent of the one or more processors 202. In one example, audio content may be processed and/or intentionally altered by the audio processing components 208 to produce audio signals. The produced audio signals may then be provided to the audio amplifier(s) 210 for amplification and playback through speaker(s) 212. Particularly, the audio amplifier(s) 210 may include devices configured to amplify audio signals to a level for driving one or more of the speakers 212. The speaker(s) 212 may include an individual transducer (e.g., a “driver”) or a complete speaker system involving an enclosure with one or more drivers. A particular driver of the speaker(s) 212 may include, for example, a subwoofer (e.g., for low frequencies), a mid-range driver (e.g., for middle frequencies), and/or a tweeter (e.g., for high frequencies). In some cases, each transducer in the one or more speakers 212 may be driven by an individual corresponding audio amplifier of the audio amplifier(s) 210. In addition to producing analog signals for playback by the playback device 200, the audio processing components 208 may be configured to process audio content to be sent to one or more other playback devices for playback.

Audio content to be processed and/or played back by the playback device 200 may be received from an external source, such as via an audio line-in input connection (e.g., an auto-detecting 3.5 mm audio line-in connection) or the network interface 214.

The network interface 214 may be configured to facilitate a data flow between the playback device 200 and one or more other devices on a data network, including but not limited to data to/from other VEDs (e.g., commands to perform an SPL measurement, SPL measurement data, commands to set a system response volume, and other data and/or commands to facilitate performance of the features and functions disclosed and described herein). As such, the playback device 200 may be configured to receive audio content over the data network from one or more other playback devices in communication with the playback device 200, network devices within a local area network, or audio content sources over a wide area network such as the Internet. The playback device 200 may transmit metadata to and/or receive metadata from other devices on the network, including but not limited to components of the networked microphone system disclosed and described herein. In one example, the audio content and other signals (e.g., metadata and other signals) transmitted and received by the playback device 200 may be transmitted in the form of digital packet data containing an Internet Protocol (IP)-based source address and IP-based destination addresses. In such a case, the network interface 214 may be configured to parse the digital packet data such that the data destined for the playback device 200 is properly received and processed by the playback device 200.

As shown, the network interface 214 may include wireless interface(s) 216 and wired interface(s) 218. The wireless interface(s) 216 may provide network interface functions for the playback device 200 to wirelessly communicate with other devices (e.g., other playback device(s), speaker(s), receiver(s), network device(s), control device(s) within a data network the playback device 200 is associated with) in accordance with a communication protocol (e.g., any wireless standard including IEEE 802.11a, 802.11b, 802.11g, 802.11n, 802.11ac, 802.15, 4G mobile communication standard, and so on). The wired interface(s) 218 may provide network interface functions for the playback device 200 to communicate over a wired connection with other devices in accordance with a communication protocol (e.g., IEEE 802.3). While the network interface 214 shown in FIG. 2 includes both wireless interface(s) 216 and wired interface(s) 218, the network interface 214 may in some embodiments include only wireless interface(s) or only wired interface(s).

The microphone(s) 220 may be arranged to detect sound in the environment of the playback device 200. For instance, the microphone(s) may be mounted on an exterior wall of a housing of the playback device. The microphone(s) may be any type of microphone now known or later developed such as a condenser microphone, electret condenser microphone, or a dynamic microphone. The microphone(s) may be sensitive to a portion of the frequency range of the speaker(s) 220. One or more of the speaker(s) 220 may operate in reverse as the microphone(s) 220. In some aspects, the playback device 200 might not have microphone(s) 220.

In one example, the playback device 200 and one other playback device may be paired to play two separate audio components of audio content. For instance, playback device 200 may be configured to play a left channel audio component, while the other playback device may be configured to play a right channel audio component, thereby producing or enhancing a stereo effect of the audio content. The paired playback devices (also referred to as “bonded playback devices”, “bonded group”, or “stereo pair”) may further play audio content in synchrony with other playback devices.

In another example, the playback device 200 may be sonically consolidated with one or more other playback devices to form a single, consolidated playback device. A consolidated playback device may be configured to process and reproduce sound differently than an unconsolidated playback device or playback devices that are paired, because a consolidated playback device may have additional speaker drivers through which audio content may be rendered. For instance, if the playback device 200 is a playback device designed to render low frequency range audio content (i.e. a subwoofer), the playback device 200 may be consolidated with a playback device designed to render full frequency range audio content. In such a case, the full frequency range playback device, when consolidated with the low frequency playback device 200, may be configured to render only the mid and high frequency components of audio content, while the low frequency range playback device 200 renders the low frequency component of the audio content. The consolidated playback device may further be paired with a single playback device or yet another consolidated playback device.

By way of illustration, Sonos, Inc. presently offers (or has offered) for sale certain playback devices including a “PLAY:1,” “PLAY:3,” “PLAY:5,” “PLAYBAR,” “CONNECT:AMP,” “CONNECT,” and “SUB.” Any other past, present, and/or future playback devices may additionally or alternatively be used to implement the playback devices of example embodiments disclosed herein. Additionally, it is understood that a playback device is not limited to the example illustrated in FIG. 2 or to the Sonos product offerings. For example, a playback device may include a wired or wireless headphone. In another example, a playback device may include or interact with a docking station for personal mobile media playback devices. In yet another example, a playback device may be integral to another device or component such as a television, a lighting fixture, or some other device for indoor or outdoor use.

b. Example Playback Zone Configurations

Referring back to the media playback system 100 of FIG. 1, the environment may have one or more playback zones, each with one or more playback devices and/or other VEDs. The media playback system 100 may be established with one or more playback zones, after which one or more zones may be added, or removed to arrive at the example configuration shown in FIG. 1. Each zone may be given a name according to a different room or space such as an office, bathroom, master bedroom, bedroom, kitchen, dining room, living room, and/or balcony. In one case, a single playback zone may include multiple rooms or spaces. In another case, a single room or space may include multiple playback zones.

As shown in FIG. 1, the balcony, dining room, kitchen, bathroom, office, and bedroom zones each have one playback device, while the living room and master bedroom zones each have multiple playback devices. In the living room zone, playback devices 104, 106, 108, and 110 may be configured to play audio content in synchrony as individual playback devices, as one or more bonded playback devices, as one or more consolidated playback devices, or any combination thereof. Similarly, in the case of the master bedroom, playback devices 122 and 124 may be configured to play audio content in synchrony as individual playback devices, as a bonded playback device, or as a consolidated playback device.

In one example, one or more playback zones in the environment of FIG. 1 may each be playing different audio content. For instance, the user may be grilling in the balcony zone and listening to hip hop music being played by the playback device 102 while another user may be preparing food in the kitchen zone and listening to classical music being played by the playback device 114. In another example, a playback zone may play the same audio content in synchrony with another playback zone. For instance, the user may be in the office zone where the playback device 118 is playing the same rock music that is being playing by playback device 102 in the balcony zone. In such a case, playback devices 102 and 118 may be playing the rock music in synchrony such that the user may seamlessly (or at least substantially seamlessly) enjoy the audio content that is being played out-loud while moving between different playback zones. Synchronization among playback zones may be achieved in a manner similar to that of synchronization among playback devices, as described in previously referenced U.S. Pat. No. 8,234,395.

As suggested above, the zone configurations of the media playback system 100 may be dynamically modified, and in some embodiments, the media playback system 100 supports numerous configurations. For instance, if a user physically moves one or more playback devices to or from a zone, the media playback system 100 may be reconfigured to accommodate the change(s). For instance, if the user physically moves the playback device 102 from the balcony zone to the office zone, the office zone may now include both the playback device 118 and the playback device 102. The playback device 102 may be paired or grouped with the office zone and/or renamed if so desired via a control device such as the control devices 126 and 128. On the other hand, if the one or more playback devices are moved to a particular area in the home environment that is not already a playback zone, a new playback zone may be created for the particular area.

Further, different playback zones of the media playback system 100 may be dynamically combined into zone groups or split up into individual playback zones. For instance, the dining room zone and the kitchen zone may be combined into a zone group for a dinner party such that playback devices 112 and 114 may render (e.g., play back) audio content in synchrony. On the other hand, the living room zone may be split into a television zone including playback device 104, and a listening zone including playback devices 106, 108, and 110, if the user wishes to listen to music in the living room space while another user wishes to watch television.

c. Example Control Devices

FIG. 3 shows a functional block diagram of an example control device 300 that may be configured to be one or both of the control devices 126 and 128 of the media playback system 100. As shown, the control device 300 may include one or more processors 302, memory 304, a network interface 306, a user interface 308, microphone(s) 310, and software components 312. In one example, the control device 300 may be a dedicated controller for the media playback system 100. In another example, the control device 300 may be a network device on which media playback system controller application software may be installed, such as for example, an iPhone™, iPad™ or any other smart phone, tablet or network device (e.g., a networked computer such as a PC or Mac™).

The one or more processors 302 may be configured to perform functions relevant to facilitating user access, control, and configuration of the media playback system 100. The memory 304 may be data storage that can be loaded with one or more of the software components executable by the one or more processors 302 to perform those functions. The memory 304 may also be configured to store the media playback system controller application software and other data associated with the media playback system 100 and the user.

In one example, the network interface 306 may be based on an industry standard (e.g., infrared, radio, wired standards including IEEE 802.3, wireless standards including IEEE 802.11a, 802.11b, 802.11g, 802.11n, 802.11ac, 802.15, 3G, 4G, or 5G mobile communication standards, and so on). The network interface 306 may provide a means for the control device 300 to communicate with other devices in the media playback system 100. In one example, data and information (e.g., such as a state variable) may be communicated between control device 300 and other devices via the network interface 306. For instance, playback zone and zone group configurations in the media playback system 100 may be received by the control device 300 from a playback device or another network device, or transmitted by the control device 300 to another playback device or network device via the network interface 306. In some cases, the other network device may be another control device.

Playback device control commands such as volume control and audio playback control may also be communicated from the control device 300 to a playback device via the network interface 306. As suggested above, changes to configurations of the media playback system 100 may also be performed by a user using the control device 300. The configuration changes may include adding/removing one or more playback devices to/from a zone, adding/removing one or more zones to/from a zone group, forming a bonded or consolidated player, separating one or more playback devices from a bonded or consolidated player, among others. Accordingly, the control device 300 may sometimes be referred to as a controller, whether the control device 300 is a dedicated controller or a network device on which media playback system controller application software is installed.

Control device 300 may include microphone(s) 310. Microphone(s) 310 may be arranged to detect sound in the environment of the control device 300. Microphone(s) 310 may be any type of microphone now known or later developed such as a condenser microphone, electret condenser microphone, or a dynamic microphone. The microphone(s) may be sensitive to a portion of a frequency range. Two or more microphones 310 may be arranged to capture location information of an audio source (e.g., voice, audible sound) and/or to assist in filtering background noise.

The user interface 308 of the control device 300 may be configured to facilitate user access and control of the media playback system 100, by providing a controller interface such as the example controller interface 400 shown in FIG. 4. The controller interface 400 includes a playback control region 410, a playback zone region 420, a playback status region 430, a playback queue region 440, and an audio content sources region 450. The user interface 400 as shown is just one example of a user interface that may be provided on a network device such as the control device 300 of FIG. 3 (and/or the control devices 126 and 128 of FIG. 1) and accessed by users to control a media playback system such as the media playback system 100. Other user interfaces of varying formats, styles, and interactive sequences may alternatively be implemented on one or more network devices to provide comparable control access to a media playback system.

The playback control region 410 may include selectable (e.g., by way of touch or by using a cursor) icons to cause playback devices in a selected playback zone or zone group to play or pause, fast forward, rewind, skip to next, skip to previous, enter/exit shuffle mode, enter/exit repeat mode, enter/exit cross fade mode. The playback control region 410 may also include selectable icons to modify equalization settings, and playback volume, among other possibilities.

The playback zone region 420 may include representations of playback zones within the media playback system 100. In some embodiments, the graphical representations of playback zones may be selectable to bring up additional selectable icons to manage or configure the playback zones in the media playback system, such as a creation of bonded zones, creation of zone groups, separation of zone groups, and renaming of zone groups, among other possibilities.

For example, as shown, a “group” icon may be provided within each of the graphical representations of playback zones. The “group” icon provided within a graphical representation of a particular zone may be selectable to bring up options to select one or more other zones in the media playback system to be grouped with the particular zone. Once grouped, playback devices in the zones that have been grouped with the particular zone will be configured to play audio content in synchrony with the playback device(s) in the particular zone. Analogously, a “group” icon may be provided within a graphical representation of a zone group. In this case, the “group” icon may be selectable to bring up options to deselect one or more zones in the zone group to be removed from the zone group. Other interactions and implementations for grouping and ungrouping zones via a user interface such as the user interface 400 are also possible. The representations of playback zones in the playback zone region 420 may be dynamically updated as playback zone or zone group configurations are modified.

The playback status region 430 may include graphical representations of audio content that is presently being played, previously played, or scheduled to play next in the selected playback zone or zone group. The selected playback zone or zone group may be visually distinguished on the user interface, such as within the playback zone region 420 and/or the playback status region 430. The graphical representations may include track title, artist name, album name, album year, track length, and other relevant information that may be useful for the user to know when controlling the media playback system via the user interface 400.

The playback queue region 440 may include graphical representations of audio content in a playback queue associated with the selected playback zone or zone group. In some embodiments, each playback zone or zone group may be associated with a playback queue containing information corresponding to zero or more audio items for playback by the playback zone or zone group. For instance, each audio item in the playback queue may comprise a uniform resource identifier (URI), a uniform resource locator (URL) or some other identifier that may be used by a playback device in the playback zone or zone group to find and/or retrieve the audio item from a local audio content source or a networked audio content source, possibly for playback by the playback device.

In one example, a playlist may be added to a playback queue, in which case information corresponding to each audio item in the playlist may be added to the playback queue. In another example, audio items in a playback queue may be saved as a playlist. In a further example, a playback queue may be empty, or populated but “not in use” when the playback zone or zone group is playing continuously streaming audio content, such as Internet radio that may continue to play until otherwise stopped, rather than discrete audio items that have playback durations. In an alternative embodiment, a playback queue can include Internet radio and/or other streaming audio content items and be “in use” when the playback zone or zone group is playing those items. Other examples are also possible.

When playback zones or zone groups are “grouped” or “ungrouped,” playback queues associated with the affected playback zones or zone groups may be cleared or re-associated. For example, if a first playback zone including a first playback queue is grouped with a second playback zone including a second playback queue, the established zone group may have an associated playback queue that is initially empty, that contains audio items from the first playback queue (such as if the second playback zone was added to the first playback zone), that contains audio items from the second playback queue (such as if the first playback zone was added to the second playback zone), or a combination of audio items from both the first and second playback queues. Subsequently, if the established zone group is ungrouped, the resulting first playback zone may be re-associated with the previous first playback queue, or be associated with a new playback queue that is empty or contains audio items from the playback queue associated with the established zone group before the established zone group was ungrouped. Similarly, the resulting second playback zone may be re-associated with the previous second playback queue, or be associated with a new playback queue that is empty, or contains audio items from the playback queue associated with the established zone group before the established zone group was ungrouped. Other examples are also possible.

Referring back to the user interface 400 of FIG. 4, the graphical representations of audio content in the playback queue region 440 may include track titles, artist names, track lengths, and other relevant information associated with the audio content in the playback queue. In one example, graphical representations of audio content may be selectable to bring up additional selectable icons to manage and/or manipulate the playback queue and/or audio content represented in the playback queue. For instance, a represented audio content may be removed from the playback queue, moved to a different position within the playback queue, or selected to be played immediately, or after any currently playing audio content, among other possibilities. A playback queue associated with a playback zone or zone group may be stored in a memory on one or more playback devices in the playback zone or zone group, on a playback device that is not in the playback zone or zone group, and/or some other designated device.

The audio content sources region 450 may include graphical representations of selectable audio content sources from which audio content may be retrieved and played by the selected playback zone or zone group. Discussions pertaining to audio content sources may be found in the following section.

d. Example Audio Content Sources

As indicated previously, one or more playback devices in a zone or zone group may be configured to retrieve for playback audio content (e.g. according to a corresponding URI or URL for the audio content) from a variety of available audio content sources. In one example, audio content may be retrieved by a playback device directly from a corresponding audio content source (e.g., a line-in connection). In another example, audio content may be provided to a playback device over a network via one or more other playback devices or network devices.

Example audio content sources may include a memory of one or more playback devices in a media playback system such as the media playback system 100 of FIG. 1, local music libraries on one or more network devices (such as a control device, a network-enabled personal computer, or a networked-attached storage (NAS), for example), streaming audio services providing audio content via the Internet (e.g., the cloud), or audio sources connected to the media playback system via a line-in input connection on a playback device or network devise, among other possibilities.

In some embodiments, audio content sources may be regularly added or removed from a media playback system such as the media playback system 100 of FIG. 1. In one example, an indexing of audio items may be performed whenever one or more audio content sources are added, removed or updated. Indexing of audio items may involve scanning for identifiable audio items in all folders/directory shared over a network accessible by playback devices in the media playback system, and generating or updating an audio content database containing metadata (e.g., title, artist, album, track length, among others) and other associated information, such as a URI or URL for each identifiable audio item found. Other examples for managing and maintaining audio content sources may also be possible.

The above discussions relating to playback devices, controller devices, playback zone configurations, and media content sources provide only some examples of operating environments within which functions and methods described below may be implemented. Other operating environments and configurations of media playback systems, playback devices, and network devices not explicitly described herein may also be applicable and suitable for implementation of the functions and methods.

e. Example Plurality of Network devices

FIG. 5 shows an example plurality of network devices 500 that can be configured to provide an audio playback experience with voice control. One having ordinary skill in the art will appreciate that the devices shown in FIG. 5 are for illustrative purposes only, and variations including different and/or additional (or fewer) devices may be possible. As shown, the plurality of network devices 500 includes computing devices 504, 506, and 508; network microphone devices (NMDs) 512, 514, 516, and 518; playback devices (PBDs) 532, 534, 536, and 538; and a controller device 522. As described previously, any one or more (or all) of the NMDs 512-16, PBDs 532-38, and/or controller device 522 may be VEDs. For example, in some embodiments PBD 532 and 536 may be VEDs, while PBD 534 and 538 may not be VEDs.

Each of the plurality of network devices 500 are network-capable devices that can establish communication with one or more other devices in the plurality of devices according to one or more network protocols, such as NFC, Bluetooth™, Ethernet, and IEEE 802.11, among other examples, over one or more types of networks, such as wide area networks (WAN), local area networks (LAN), and personal area networks (PAN), among other possibilities.

As shown, the computing devices 504, 506, and 508 are part of a cloud network 502. The cloud network 502 may include additional computing devices (not shown). In one example, the computing devices 504, 506, and 508 may be different servers. In another example, two or more of the computing devices 504, 506, and 508 may be modules of a single server. Analogously, each of the computing device 504, 506, and 508 may include one or more modules or servers. For ease of illustration purposes herein, each of the computing devices 504, 506, and 508 may be configured to perform particular functions within the cloud network 502. For instance, computing device 508 may be a source of audio content for a streaming music service, while computing device 506 may be associated a voice-assistant service (e.g., an Alexa®, Google Assistant®, or other voice service) for processing voice input that has been captured after detection of the wake word. As an example, a VED may transmit a captured voice input (e.g., a voice utterance and a wake word) or a portion thereof (e.g., just voice utterance following the wake word) over a data network to the computing device 506 for speech processing. The computing device 506 may employ a text to speech engine to convert a voice input into text, which can be processed to determine an underlying intent of a voice utterance. The computing device 506 or another computing device can send a corresponding response to the voice input to a VED, such as a response comprising as its payload one or more of an audible output (e.g., a voice response to a query and/or an acknowledgment) and/or an instruction intended for one or more of the network devices of local system. The instruction may include, for example, a command for initiating, pausing, resuming, or stopping playback of audio content on one or more network devices, increasing/decreasing playback volume, retrieving a track or playlist corresponding to an audio queue via a certain URI or URL, etc. Additional examples of voice processing to determine intent and responding to voice inputs can be found, for example, in previously referenced U.S. patent application Ser. No. 15/721,141.

As shown, the computing device 504 may be configured to interface with NMDs 512, 514, and 516 via communication path 542. NMDs 512, 514, and 516 may be components of one or more “Smart Home” systems. In one case, NMDs 512, 514, and 516 may be physically distributed throughout a household, similar to the distribution of devices shown in FIG. 1. In another case, two or more of the NMDs 512, 514, and 516 may be physically positioned within relative close proximity of one another. Communication path 542 may comprise one or more types of networks, such as a WAN including the Internet, LAN, and/or PAN, among other possibilities.

In one example, one or more of the NMDs 512, 514, and 516 are devices configured primarily for audio detection. In another example, one or more of the NMDs 512, 514, and 516 may be components of devices having various primary utilities. For instance, as discussed above in connection to FIGS. 2 and 3, one or more of NMDs 512, 514, and 516 may be (or at least may include or be a component of) the microphone(s) 220 of playback device 200 or the microphone(s) 310 of network device 300. Further, in some cases, one or more of NMDs 512, 514, and 516 may be (or at least may include or be a component of) the playback device 200 or network device 300. In an example, one or more of NMDs 512, 514, and/or 516 may include multiple microphones arranged in a microphone array. In some embodiments, one or more of NMDs 512, 514, and/or 516 may be a microphone on a mobile computing device (e.g., a smartphone, tablet, or other computing device).

As shown, the computing device 506 is configured to interface with controller device 522 and PBDs 532, 534, 536, and 538 via communication path 544. In one example, controller device 522 may be a network device such as the network device 200 of FIG. 2. Accordingly, controller device 522 may be configured to provide the controller interface 400 of FIG. 4. Similarly, PBDs 532, 534, 536, and 538 may be playback devices such as the playback device 300 of FIG. 3. As such, PBDs 532, 534, 536, and 538 may be physically distributed throughout a household as shown in FIG. 1. For illustration purposes, PBDs 536 and 538 are shown as members of a bonded zone 530, while PBDs 532 and 534 are members of their own respective zones. As described above, the PBDs 532, 534, 536, and 538 may be dynamically bonded, grouped, unbonded, and ungrouped. Communication path 544 may comprise one or more types of networks, such as a WAN including the Internet, LAN, and/or PAN, among other possibilities.

In one example, as with NMDs 512, 514, and 516, controller device 522 and PBDs 532, 534, 536, and 538 may also be components of one or more “Smart Home” systems. In one case, PBDs 532, 534, 536, and 538 may be distributed throughout the same household as the NMDs 512, 514, and 516. Further, as suggested above, one or more of PBDs 532, 534, 536, and 538 may be one or more of NMDs 512, 514, and 516. For example, any one or more (or perhaps all) of NMDs 512-16, PBDs 532-38, and/or controller device 522 may be voice-enabled devices (VEDs).

The NMDs 512, 514, and 516 may be part of a local area network, and the communication path 542 may include an access point that links the local area network of the NMDs 512, 514, and 516 to the computing device 504 over a WAN (communication path not shown). Likewise, each of the NMDs 512, 514, and 516 may communicate with each other via such an access point.

Similarly, controller device 522 and PBDs 532, 534, 536, and 538 may be part of a local area network and/or a local playback network as discussed in previous sections, and the communication path 544 may include an access point that links the local area network and/or local playback network of controller device 522 and PBDs 532, 534, 536, and 538 to the computing device 506 over a WAN. As such, each of the controller device 522 and PBDs 532, 534, 536, and 538 may also communicate with each over such an access point.

In one example, communication paths 542 and 544 may comprise the same access point. In an example, each of the NMDs 512, 514, and 516, controller device 522, and PBDs 532, 534, 536, and 538 may access the cloud network 502 via the same access point for a household.

As shown in FIG. 5, each of the NMDs 512, 514, and 516, controller device 522, and PBDs 532, 534, 536, and 538 may also directly communicate with one or more of the other devices via communication means 546. Communication means 546 as described herein may involve and/or include one or more forms of communication between the devices, according to one or more network protocols, over one or more types of networks, and/or may involve communication via one or more other network devices. For instance, communication means 546 may include one or more of for example, Bluetooth™ (IEEE 802.15), NFC, Wireless direct, and/or Proprietary wireless, among other possibilities.

In one example, controller device 522 may communicate with NMD 512 over Bluetooth™, and communicate with PBD 534 over another local area network. In another example, NMD 514 may communicate with controller device 522 over another local area network, and communicate with PBD 536 over Bluetooth™. In a further example, each of the PBDs 532, 534, 536, and 538 may communicate with each other according to a spanning tree protocol over a local playback network, while each communicating with controller device 522 over a local area network, different from the local playback network. Other examples are also possible.

In some cases, communication means between the NMDs 512, 514, and 516, controller device 522, and PBDs 532, 534, 536, and 538 may be different (or perhaps change) depending on types of communication requirements between the devices, network conditions, and/or latency demands. For instance, communication means 546 may be used when NMD 516 is first introduced to the household with the PBDs 532, 534, 536, and 538. In one case, the NMD 516 may transmit identification information corresponding to the NMD 516 to PBD 538 via NFC, and PBD 538 may in response, transmit local area network information to NMD 516 via NFC (or some other form of communication). However, once NMD 516 has been configured within the household, communication means between NMD 516 and PBD 538 may change. For instance, NMD 516 may subsequently communicate with PBD 538 via communication path 542, the cloud network 502, and communication path 544. In another example, the NMDs and PBDs may never communicate via local communications means 546. In a further example, the NMDs and PBDs may communicate primarily via local communications means 546. Other examples are also possible.

In an illustrative example, NMDs 512, 514, and 516 may be configured to receive voice inputs to control PBDs 532, 534, 536, and 538. The available control commands may include any media playback system controls previously discussed, such as playback volume control, playback transport controls, music source selection, and grouping, among other possibilities. In one instance, NMD 512 may receive a voice input to control one or more of the PBDs 532, 534, 536, and 538. In response to receiving the voice input, NMD 512 may transmit via communication path 542, the voice input to computing device 504 for processing. In one example, the computing device 504 may convert the voice input to an equivalent text command, and parse the text command to identify a command. Computing device 504 may then subsequently transmit the text command to the computing device 506, and computing device 506 in turn may then control one or more of PBDs 532-538 to execute the command. In another example, the computing device 504 may convert the voice input to an equivalent text command, and then subsequently transmit the text command to the computing device 506. The computing device 506 may then parse the text command to identify one or more playback commands, and then computing device 506 may additionally control one or more of PBDs 532-538 to execute the command.

For instance, if the text command is “Play ‘Track 1’ by ‘Artist 1’ from ‘Streaming Service 1’ in ‘Zone 1’,” The computing device 506 may identify (i) a URL for “Track 1” by “Artist 1” available from “Streaming Service 1,” and (ii) at least one playback device in “Zone 1.” In this example, the URL for “Track 1” by “Artist 1” from “Streaming Service 1” may be a URL pointing to computing device 508, and “Zone 1” may be the bonded zone 530. As such, upon identifying the URL and one or both of PBDs 536 and 538, the computing device 506 may transmit via communication path 544 to one or both of PBDs 536 and 538, the identified URL for playback. One or both of PBDs 536 and 538 may responsively retrieve audio content from the computing device 508 according to the received URL, and begin playing “Track 1” by “Artist 1” from “Streaming Service 1.”

One having ordinary skill in the art will appreciate that the above are just some illustrative examples, and that other implementations are also possible. In one case, operations performed by one or more of the plurality of network devices 500, as described above, may be performed by one or more other devices in the plurality of network devices 500. For instance, the conversion from voice input to the text command may be alternatively, partially, or wholly performed by another device or devices, such as controller device 522, NMD 512, computing device 506, PBD 536, and/or PBD 538. Analogously, the identification of the URL may be alternatively, partially, or wholly performed by another device or devices, such as NMD 512, computing device 504, PBD 536, and/or PBD 538.

f. Example Network Microphone Device

FIG. 6 shows a function block diagram of an example network microphone device 600 that may be configured to be one or more of NMDs 512, 514, and 516 of FIG. 5, and/or any of the VEDs disclosed and described herein. As shown, the network microphone device 600 includes one or more processors 602, tangible, non-transitory computer-readable memory 604, a microphone array 606 (e.g., one or more microphones), a network interface 608, a user interface 610, software components 612, and speaker(s) 614. One having ordinary skill in the art will appreciate that other network microphone device configurations and arrangements are also possible. For instance, network microphone devices may alternatively exclude the speaker(s) 614 or have a single microphone instead of microphone array 606.

The one or more processors 602 may include one or more processors and/or controllers, which may take the form of a general or special-purpose processor or controller. For instance, the one or more processors 602 may include microprocessors, microcontrollers, application-specific integrated circuits, digital signal processors, and the like. The tangible, non-transitory computer-readable memory 604 may be data storage that can be loaded with one or more of the software components executable by the one or more processors 602 to perform those functions. Accordingly, memory 604 may comprise one or more non-transitory computer-readable storage mediums, examples of which may include volatile storage mediums such as random access memory, registers, cache, etc. and non-volatile storage mediums such as read-only memory, a hard-disk drive, a solid-state drive, flash memory, and/or an optical-storage device, among other possibilities.

The microphone array 606 may be a plurality of microphones arranged to detect sound in the environment of the network microphone device 600. Microphone array 606 may include any type of microphone now known or later developed such as a condenser microphone, electret condenser microphone, or a dynamic microphone, among other possibilities. In one example, the microphone array may be arranged to detect audio from one or more directions relative to the network microphone device. The microphone array 606 may be sensitive to a portion of a frequency range. In one example, a first subset of the microphone array 606 may be sensitive to a first frequency range, while a second subset of the microphone array may be sensitive to a second frequency range. The microphone array 606 may further be arranged to capture location information of an audio source (e.g., voice, audible sound) and/or to assist in filtering background noise. Notably, in some embodiments the microphone array may consist of only a single microphone, rather than a plurality of microphones.

The network interface 608 may be configured to facilitate wireless and/or wired communication between various network devices, such as, in reference to FIG. 5, controller device 522, PBDs 532-538, computing devices 504-508 in cloud network 502, and other network microphone devices, among other possibilities. As such, network interface 608 may take any suitable form for carrying out these functions, examples of which may include an Ethernet interface, a serial bus interface (e.g., FireWire, USB 2.0, etc.), a chipset and antenna adapted to facilitate wireless communication, and/or any other interface that provides for wired and/or wireless communication. In one example, the network interface 608 may be based on an industry standard (e.g., infrared, radio, wired standards including IEEE 802.3, wireless standards including IEEE 802.11a, 802.11b, 802.11g, 802.11n, 802.11ac, 802.15, 4G mobile communication standard, and so on).

The user interface 610 of the network microphone device 600 may be configured to facilitate user interactions with the network microphone device. In one example, the user interface 610 may include one or more of physical buttons, graphical interfaces provided on touch sensitive screen(s) and/or surface(s), among other possibilities, for a user to directly provide input to the network microphone device 600. The user interface 610 may further include one or more of lights and the speaker(s) 614 to provide visual and/or audio feedback to a user. In one example, the network microphone device 600 may further be configured to playback audio content via the speaker(s) 614.

III. Example Noise Suppression Systems and Methods

FIGS. 7A-7C depict network devices 700 (identified individually as network devices 700a-700d). Each of the network devices 700 comprises a housing 704 that at least partially encloses certain components (not shown) of the network device within an enclosure, such as the amplifiers, transducers, processors, and antenna. The network devices 700 further comprise microphones 702 (identified individually as microphones 702a-g) disposed at various locations of the housing 704. For example, network device 700a comprises a structured array of the microphones 702. In some embodiments, the microphones 702 may be seated within and/or exposed through an aperture in the housing 704. Network device 700a may be configured to be one or more of NMDs 512, 514, and 516 of FIG. 5, and/or any of the VEDs disclosed and described herein.

As discussed above, embodiments described herein facilitate suppressing noise from audio content captured by multiple microphones in order to help detect the presence of a wake word in the captured audio content. Some noise suppression processes involve single-microphone techniques for suppressing certain frequencies at which noise is dominant over speech content. However, these techniques can result in significant distortion of the speech content. Other noise suppression processes involve beamforming techniques in which a structured array of microphones is used to capture audio content from specific directions where speech is dominant over noise content and disregard audio content from directions where noise is dominant over speech content.

While effective for suppressing unwanted noise when capturing audio content, beamforming has limitations. For example, traditional beamforming may be generally suboptimal at detecting voice input compared to the enhanced suppression techniques described below. FIG. 11, for example, shows significant wake word detection improvement using a multi-channel Wiener filter (MCWF) algorithm described below relative to traditional static beamforming under the same conditions, which involved (1) detecting a wake word from a noisy sound sample having an SNR of −15 dB (2) while playing back the same sample audio track (“Relax” by Frankie Goes to Hollywood), and (3) using the same NMD for each test (the NMD for testing had an array of six microphones spaced apart from one another within a suitable distance for traditional beamforming). FIG. 11 depicts the results for three different test cases under the test conditions: (1) plot 1110 depicting the detected sound sample without using beamforming or the MCWF algorithm, (2) plot 1120 depicting the detected sound sample using beamforming, and (3) plot 1130 depicting the detected sound sample using an MCWF-based algorithm. In each of plots 1110, 1120, and 1130, the x-axis represents time, the y-axis corresponds to frequency, and the darkness of the plot represents the intensity of the detected sound sample in dB (where intensity increases as darkness increases). Further, in each of plots 1110, 1120, and 1130, the wake word (identified in FIG. 11 by arrows) begins approximately halfway along the x-axis and ends about three-quarters along the x-axis. Comparing plot 1120 to plot 1110, it can be seen that beamforming removed some of the noise, but a significant amount of noise still remained. However, comparing plot 1130 to plot 1120, it can be seen that the MCWF algorithm filtered out substantially more noise than the beamforming, such that the wake word can be more readily identified from the MCWF filtered sound sample than from the beamforming filtered sound sample.

Additionally, beamforming typically requires a known array configuration, and the network device 700 selectively captures audio from particular directions relative to the array. Beamforming may only be feasible in scenarios in which it is possible to implement such an array of microphones 702. For instance, if the microphones 702 and processing components of the network device 700a of FIG. 7A were configured for traditional beamforming, the spacing or distance d₁between neighboring microphones 702 would be limited to a theoretical maximum of about 4.25 cm using traditional aliasing-free beamforming at frequencies up to 4 kHz. However, some network devices may not be capable of supporting an array of microphones 702 spaced so closely, due to hardware or other design constraints. Accordingly, the distance d₁between the microphones 702 in various embodiments may not be restructured to such a theoretical maximum when using the enhanced noise suppression techniques described herein.

FIG. 7B, for example, depicts the network device 700b with the microphones 702 arranged in a disarrayed fashion. As used herein, the term “disarrayed fashion” refers to any arrangement of microphones that is not used as a beamforming array. As such, microphones arranged in a disarrayed fashion may be arranged in arbitrary order relative to one another; positioned more conveniently along the housing, such as between, speakers, electronics, buttons, and/or other components; and/or arranged in some order, but in an order that does not (or at least may not) support beamforming. For instance, as shown in FIG. 7B, the microphones 702 appear to be arranged according to a particular geometric configuration, with microphones 702a, 702b, 702f, and 702g being arranged in a first horizontal plane and microphones 702c, 702d, and 702e being arranged in a second horizontal plane. However, even though the arrangement of the microphones 702 in FIG. 7B includes some aspect of order, the arrangement is referred to as “disarrayed” because the microphones 702 are too spread out from one another to perform beamforming, or at least too spread out from one another to perform beamforming effectively for the types of voice applications disclosed and described herein. In some implementations, a minimum distance between two given microphone is greater than 5 cm. For example, a spacing or distance d₂between the microphone 702c and 702d or any other set of two or more microphones may be between 5 cm and 60 cm.

FIG. 7C depicts the microphones 702 spread across multiple network devices, according to an example embodiment. In particular, microphones 702c, 702d, and 702e are disposed in the housing 704 of network device 700c, and microphones 702a, 702b, 702f, and 702g are disposed in the housing 704 of network device 700d. In some embodiments, network devices 700c and 700d are located in the same room (e.g., as separate devices in a home theater configuration), but in different areas of the room. In such embodiments, a spacing or distance between the microphones 702 on network devices 700c and 700d, such as distance d₃between microphone 702d and 702f, may exceed 60 cm. For example, distance d₃between microphone 702d and 702f or any other set of two or more microphones respectively disposed on separate network devices may be between 1 and 5 meters.

In each of the arrangements depicted in FIGS. 7A-C, the network devices 700 employ multi-microphone noise suppression techniques that do not necessarily rely on the geometrical arrangement of the microphones 702. Instead, techniques for suppressing noise in accordance with various embodiments involve linear time-invariant filtering of an observed noisy process, assuming known stationary signal and noise spectra, and additive noise. The network device 700 uses first audio content captured by one or more of the microphones 702 to estimate noise in second audio content that is concurrently being captured by one or more other ones of the microphones 702. For instance, microphone 702a captures first audio content while microphone 702g concurrently captures second audio content. If a user proximate to the network device 700 speaks a voice command, then speech content in both the first audio content captured by microphone 702a and the second audio content captured by microphone 702g includes the same voice command. Further, if a noise source is proximate to the network device 700, then both the first audio content captured by microphone 702a and the second audio content captured by microphone 702g includes noise content from the noise source.

However, because microphone 702a and 702g are spaced apart from one another, the strength of the speech content and noise content may vary between the first audio content and the second audio content. For instance, if microphone 702a is closer to the noise source and microphone 702g is closer to the speaking user, then the noise content can dominate the first audio content captured by microphone 702a, and the speech content can dominate the second audio content captured by microphone 702g. And if the noise content dominates the first audio content, then the network device 700 can use the first audio content to generate an estimate of the noise content that is present in the second audio content. The estimated noise from the first audio content can then be used to filter out noise and preserve speech in the second audio content.

In some embodiments, the network device 700 carries out this process concurrently for all of the microphones 702, such that noise content captured by each microphone is used to estimate the noise content captured by each other microphone. The network device 700 filters the respective audio signals captured by each of the microphones 702 using the estimated noise content to suppress the respective noise content in each audio signal, and then combines the filtered audio signals. With the noise content of each audio signal being suppressed, the dominant content of each audio signal is speech content, and so the combined audio signal is also speech-dominant.

An example MCWF algorithm for carrying out these processes is described in further detail below in connection with FIG. 8.

FIG. 8 depicts an example environment 800 in which such a noise suppression process is performed. The environment 800 includes multiple microphones 802 (identified individually as microphones 802a-g) for capturing audio content. The microphones 802 may be configured to be one or more of microphones 702 of FIGS. 7A-C. As shown, the environment 800 includes seven microphones 802, but in other embodiments, the environment 800 includes additional or fewer microphones. In some embodiments, the microphones 802 are arranged on or within a single network device, such as network device 700. In other embodiments, one or more of the microphones 802 are arranged on or within one network device, and the remaining microphones are arranged on or within one or more other network devices.

In practice, the microphones 802 capture audio content that reaches the microphones 802. As shown, when a person 804 speaks near the microphones 802, the person 804 produces a speech signal s(t). As the speech signal s(t) propagates throughout the environment 800, at least some of the speech signal s(t) reflects off of walls or other nearby objects in the environment 800. These reflections can distort the speech signal s(t), such that the version of the speech signal captured by the microphones 802 is a reverberated speech signal x(t) that is different from the original speech signal s(t).

Further, the environment 800 includes one or more noise sources 806, such as noise from nearby traffic or construction, noise from people moving throughout the environment, noise from one or more playback devices in the environment 800, or any other ambient noise. In some embodiments, the noise source 806 includes speech content from a person different from person 804. In any case, the noise source 806 produces a noise signal v(t) that is captured by some or all of the microphones 802. In this regard, the audio signal captured by the microphones 802 is represented as y(t), which is the sum of the reverberated speech signal x(t) and the noise signal v(t). And for each individual microphone of the microphones 802, the captured audio signal can thus be characterized as:

y_n(t)=x_n(t)+v_n(t),n=1,2, . . . ,N (Eq. 1)

where n is the index for the reference microphone, and N is the total number of microphones. Transforming from the time domain to the frequency domain, the above equation can be expressed as:

Y_n(f)=X_n(f)+V_n(f),n=1,2, . . . ,N (Eq. 2)
or, in vector form, as:
Y(f)=X(f)+V(f) (Eq. 3)

Further, power spectrum density (PSD) matrices P_yy(f), P_xx(f), and P_vv(f) are defined, where P_yy(f) is the PSD matrix for the total captured audio content, P_xx(f) is the PSD matrix for the speech portion of the total captured audio content, and P_vv(f) is the PSD matrix for the noise portion of the total captured audio content. These PSD matrices are determined using the following equations:

P_yy(f)=E{y(f)y^H(f)}, (Eq. 4)
P_xx(f)=E{x(f)x^H(f)}, (Eq. 5)
P_vv(f)=E{v(f)v^H(f)} (Eq. 6)

where E{ } represents the expected value operator and H represents the Hermitian transpose operator. Assuming a lack of correlation between the speech portion and the noise portion of the total captured audio content, which is typically the case, the PSD matrix for the speech portion of the total captured audio content can be written as:

P_xx(f)=P_yy(f)−P_vv(f). (Eq. 7)

In order to reduce the noise content V(f) and recover the speech content X(f) of the captured multi-channel audio content Y(f), the captured multi-channel audio content Y(f) is passed through a filter 808. In some embodiments, the filter 808 comprises tangible, non-transitory computer-readable media that, when executed by one or more processors of a network device, cause the network device to perform the multi-channel filtering functions disclosed and described herein.

The filter 808 can filter the captured multi-channel audio content Y(f) in various ways. In some embodiments, the filter 808 applies linear filters h_i(f) (where i=1, 2, . . . , N is the index of the reference microphone) to the vector Y(f) of the captured multi-channel audio content. In this manner, N linear filters h_i(f) (one for each of the microphones 802) are applied to the audio content vector Y(f). Applying these filters produces a filtered output Z_i(f) given by:

Z_i(f)=h_i^H(f)X(f)+h_i^H(f)V(f),i=1,2, . . . ,N. (Eq. 8)

This filtered output Z_i(f) includes a filtered speech component D_i(f) and a residual noise component v_i(f), where

D_i(f)=h_i^H(f)X(f) (Eq. 9)
and
v_i=(f)=h_i^H(f)V(f). (Eq. 10)

In order to determine the linear filters h_i(f), a set of optimization constraints are defined. In some embodiments, the optimization constraints are defined so as to maximize the extent of noise reduction while limiting the extent of signal distortion, for instance, by limiting the extent of signal distortion to be less than or equal to a threshold extent. A noise reduction factor ξ_nr(h_i(f)) is defined as:

$\begin{matrix} ξ_{nr} (h_{i} (f)) = \frac{{[u_{i} - h_{i} (f)]}^{H} P_{xx} (f) [u_{i} - h_{i} (f)]}{ϕ_{x_{i} x_{i}} (f)}, & (Eq . 11) \end{matrix}$

and a signal distortion index v_sd(h_i(f)) is defined as:

$\begin{matrix} v_{sd} (h_{i} (f)) = \frac{ϕ_{v_{i} v_{i}} (f)}{{h_{i} (f)}^{H} P_{vv} (f) h_{i} (f)}, & (Eq . 12) \end{matrix}$

where u_iis the i-th standard basis vector and is defined as

$\begin{matrix} u_{i} = {[0 \dots 0 \underset{\underset{i - th}{︸}}{1} 0 \dots 0]}^{T} . & (Eq . 13) \end{matrix}$

Thus, in order to maximize noise reduction, while limiting signal distortion, the optimization problem in some implementations is to maximize ξ_nr(h_i(f)) subject to v_sd(h_i(f))≤σ²(f). To find the solution associated with this optimization problem, the derivative of the associated Lagrangian function with respect to h_i(f) is set to zero, and the resulting closed form solution is:

h_i(f)=[P_xx(f)+βP_vv(f)]⁻P_xx(f)u_i (Eq. 14)

where β (which is a positive value and the inverse of the Lagrange multiplier) is a factor that allows for tuning the signal distortion and noise reduction at the output of h_i(f).

Implementation of such a linear filter h_i(f) can be computationally demanding. To reduce the computational complexity of the filter h_i(f), a more simplified form is obtained in some embodiments by taking advantage of the fact that the matrix P_xx(f) is a rank one matrix. And because P_xx(f) is a rank one matrix, P⁻¹_vv(f)P_xx(f) is also of rank one. In addition, the matrix inversion can be further simplified using the Woodbury matrix identity. Applying all of these concepts, the linear filter h_i(f) can be expressed as:

$\begin{matrix} h_{i} (f) = \frac{P_{vv}^{- 1} (f) P_{yy} (f) - I_{N}}{β + λ (f)} u_{i} where & (Eq . 15) \\ λ (f) = tr {P_{vv}^{- 1} (f) P_{yy} (f)} - N & (Eq . 16) \end{matrix}$

is the unique positive eigenvalue of P⁻¹_vv(f)P_xx(f) and acts as a normalizing factor.

One advantage of this linear filter h_i(f) is that it only depends on the PSD matrices for the total captured audio and the noise portion of the total captured audio, and so it does not depend on the speech portion of the total captured audio. Another advantage is that the β parameter allows for customizing the extent of noise reduction and signal distortion. For instance, increasing β increases the noise reduction at the cost of increased signal distortion, and decreasing β decreases the signal distortion at the cost of increased noise.

Because the linear filter h_i(f) depends on the PSD matrices for the total captured audio P_yy(f) and the noise portion of the total captured audio P_vv(f), these PSD matrices are estimated in order to apply the filter. In some embodiments, first order exponential smoothing is used to estimate P_yyas:

P_yy(n)=α_yP_yy(n−1)+(1−α_y)yy^H (Eq. 17)

where α_yis the smoothing coefficient and where n denotes the time-frame index. Also, for simplifying the notation, the frequency index (f) has been dropped from this equation and from the equations below, but it will be understood that the processes disclosed herein are carried out for each frequency bin. The smoothing coefficient α_yis a value between 0 and 1, and can be adjusted to tune the estimation of P_yy. Increasing α_yincreases the smoothness of the P_yyestimation by reducing the extent of change of P_yybetween consecutive time-frame indices, while reducing α_yreduces the smoothness of the P_yyestimation by increasing the extent of change of P_yybetween consecutive time-frame indices.

To estimate P_vv, the filter 808 determines, in some embodiments, whether speech content is present in each frequency bin. If the filter 808 determines that speech content is present or is likely present in a particular frequency bin, then the filter 808 determines that the frequency bin is not representative of noise content, and the filter 808 does not use that frequency bin to estimate P_vv. On the other hand, if the filter 808 determines that speech content is not present or is unlikely present in a particular frequency bin, then the filter 808 determines that the frequency bin is made up mostly or entirely of noise content, and the filter 808 then uses that noise content to estimate P.

The filter 808 can determine whether speech content is present in a frequency bin in various ways. In some embodiments, the filter 808 makes such a determination using hard voice activity detection (VAD) algorithms. In other embodiments, the filter 808 makes such a determination using softer speech presence probability algorithms. For instance, assuming a Gaussian distribution, the speech presence probability is calculated as:

$\begin{matrix} P (Speech Presence ❘ n) \overset{Δ}{=} P (H_{1} ❘ y) = {(1 + \frac{q}{1 - q} (1 + ξ) e^{- γ / (1 + ξ)})}^{- 1} & (Eq . 18) \end{matrix}$

where n is the time-frame index, where

ξ=tr{P_vv⁻¹(n−1)P_xx(n)}, (Eq. 19)
γ=y^HP_vv⁻¹(n−1)P_xx(n)P_vv⁻¹(n−1)y, (Eq. 20)
and where
q custom character P(H₀) (Eq. 21)

is the a priori probability of speech absence. The derivation of this speech presence probability is described in Souden et al., “Gaussian Model-Based Multichannel Speech Presence Probability,” IEEE Transactions on Audio, Speech, and Language Processing (2010), which is hereby incorporated by reference in its entirety.

Notably, the speech presence probability calculation depends on the PSD matrix of the speech content P_xx. However, because P_xx(f)=P_yy(f)−P_vv(f), this dependency can be removed by rewriting y as:

γ=y^HP_vv⁻¹(n−1)P_yy(n)P_vv⁻¹(n−1)y−y^HP_vv⁻¹(n−1)y (Eq. 22)

Further, the variable ξ can be written as:

$\begin{matrix} ξ = \hat{ψ} - N, where & (Eq . 23) \\ \begin{matrix} \hat{ψ} = tr {P_{vv}^{- 1} (n - 1) P_{yy} (n)} \\ = tr {P_{vv}^{- 1} (n - 1) (α_{y} P_{yy} (n - 1) + (1 - α_{y}) {yy}^{H})} \\ = α_{y} tr {P_{vv}^{- 1} (n - 1) P_{yy} (n - 1)} + \\ (1 - α_{y}) tr {y^{H} P_{vv}^{- 1} (n - 1) y} \\ = α_{y} λ (n - 1) + (1 - α_{y}) ψ, where \end{matrix} & (Eq . 24) \\ λ (n) = tr {P_{vv}^{- 1} (n) P_{yy} (n)}, and where & (Eq . 25) \\ ψ = y^{H} P_{vv}^{- 1} (n - 1) y . & (Eq . 26) \end{matrix}$

The computational complexity of the speech presence probability calculation can be further reduced by defining the vector:

y_temp=P_vv⁻¹(n−1)y (Eq. 27)

such that ψ can be written as:

ψ=y^HP_vv⁻¹(n−1)y=y^Hy_temp (Eq. 28)

and γ can be written as:

γ=y_temp^HP_yy(n)y_temp−ψ. (Eq. 29)

Accordingly, by calculating Y_tempbefore attempting to calculate ψ or γ, duplicate calculations can be avoided when the filter 808 determines the speech presence probability.

Once the speech presence probability is determined for a given time-frame, the filter 808 updates the estimate of the noise covariance matrix by employing the expectation operator according to the following equation:

$\begin{matrix} \begin{matrix} P_{vv} (n) = E {{vv}^{H} | P (H_{1})} \\ = P (H_{1} | y) P_{vv} (n - 1) + (1 - P (H_{1} | y)) \\ (α_{v} P_{vv} (n - 1) + (1 - α_{v}) {yy}^{H}) \\ = P_{vv} (n - 1) + (1 -) {yy}^{H} \end{matrix} where & (Eq . 30) \\ (Eq . 31) \end{matrix}$

is the effective frequency-dependent smoothing coefficient.

In order to get the updated P⁻¹_vv(n) for use in h_i(f), the Sherman-Morrison formula is used as follows:

$\begin{matrix} k (n) = \frac{P_{vv}^{- 1} (n - 1) y}{w + y^{H} P_{vv}^{- 1} (n - 1) y} = \frac{y_{temp}}{w + ψ} & (Eq . 32) \\ \begin{matrix} P_{vv}^{- 1} (n) = 1 (P_{vv}^{- 1} (n - 1) - k (n) y^{H} P_{vv}^{- 1} (n - 1)) \\ = 1 (P_{vv}^{- 1} (n - 1) - k (n) y_{temp}^{H}) \end{matrix} where & (Eq . 33) \\ w = \max (1 -, eps) . & (Eq . 34) \end{matrix}$

Once the updated P⁻¹_vv(n) is determined, the filter 808 can determine and apply the linear filter h_i(n), for all values off and all values of i, to the captured audio content. The output of the filter 808 is then given as y_o,i(n)=h^H_i(n)y(n). In some embodiments, the filter 808 computes the output in parallel for all i using a matrix H(n) in which the columns are h_i(n) such that

$\begin{matrix} H = \frac{P_{vv}^{- 1} (n) P_{yy} (n) - I_{N}}{β + ξ} and & (Eq . 35) \\ y_{out} = H^{H} y, where & (Eq . 36) \\ λ (n) = tr {P_{vv}^{- 1} (n) P_{yy} (n)} and & (Eq . 37) \\ ξ = λ (n) - N . & (Eq . 38) \end{matrix}$

In some embodiments, the filter 808 does not calculate H directly, which requires matrix by matrix multiplication. Instead, the computational complexity is reduced significantly by the filter 808 computing the output as follows:

$\begin{matrix} \hat{y} = P_{vv}^{- 1} (n) y and & (Eq . 39) \\ y_{out} = \frac{1}{β + ξ} (P_{yy} (n) \hat{y} - y) . & (Eq . 40) \end{matrix}$

Employing the above concepts, the filter 808 suppresses noise and preserves speech content in a multi-channel audio signal captured by the microphones 802. In a simplified manner this may comprise

- A. Update P_yy(n) for all f
- B. Calculate the speech presence probability P(H₁|y(n)) for all f
- C. Update P⁻¹_vv(n) for all f using the speech presence probability
- D. Compute the linear filter h_i(n) for all f and all i, and calculate the output as yo,i(n)=h^H_i(n)y(n)

A more detailed example may comprise carrying out the following steps.

Step 1: Initialize parameters and state variables at time-frame 0. In some embodiments, P_yyand P⁻¹_vvare initialized by estimating P_yyfor a certain period of time (e.g., 500 ms) and then using the estimated P_yyto initialize P⁻¹_vvas its inverse.

Step 2: At each time-frame n, perform the following steps 3-13.

Step 3: For each frequency index f={1, . . . , K}, update the estimate of P_yy(n) according to Equation 17, compute y_tempaccording to Equation 27, and compute ψ according to Equation 28.

Step 4: For each frequency index f={1, . . . , K}, use vector operations to compute {circumflex over (ψ)} according to Equation 24.

Step 5: For each frequency index f={1, . . . , K}, use vector operations to compute ξ according to Equation 23.

Step 6: For each frequency index f={1, . . . , K}, compute γ according to Equation 29.

Step 7: Compute the speech presence probability over all frequency bins using vector operations according to Equation 18.

Step 8: Compute the effective smoothing coefficient {circumflex over (α)}_vfor updating P_vv(n) according to Equations 30 and 31.

Step 9: Compute w according to Equation 34.

Step 10: For each frequency index f={1, . . . , K}, update k(n) according to Equation 32, and update P⁻¹_vv(n) according to Equation 33.

Step 11: For each frequency index f={1, . . . , K}, update λ(n) according to Equation 37.

Step 12: Compute ξ according to Equation 38.

Step 13: For each frequency index f={1, . . . , K}, compute the output vector of size N×1 by computing {circumflex over (γ)} according to Equation 39 and computing the output y_outaccording to Equation 40.

In addition to the other advantages already described, the above MCWF-based processing provides further advantages. For example, the filtering of the captured audio signals is carried out in a distributed manner, such that the audio signals do not need to be aggregated at a central node for processing. Further, the MCWF algorithm can be executed at an individual node where a microphone is present, and that node can then share its output from the MCWF algorithm with some or all of the other nodes in a networked system. For instance, each microphone of the microphones 702 in FIG. 7C is part of a respective node capable of executing the MCWF algorithm. As such, the node that includes microphone 702a processes the audio captured by microphone 702a in accordance with the MCWF algorithm, and then provides the MCWF output to the nodes associated with microphones 702b-g. Similarly, the node that includes microphone 702a receives the MCWF output from each of the nodes associated with microphones 702b-g. Each node can thus use the MCWF output from the other nodes when estimating and filtering out noise content in accordance with the MCWF algorithm.

Referring back to FIG. 8, once the filter 808 suppresses the noise content and preserves the speech content from the respective audio signals captured by the microphones 802, for instance using the MCWF algorithm described above, the filter 808 combines the filtered audio signals into a single signal. With the noise content of each audio signal being suppressed and the speech content being preserved, this combined signal similarly has suppressed noise content and preserved speech content.

The filter 808 provides the combined signal to a speech processing block 810 for further processing. The speech processing block 810 runs a wake word detection procedure for the output of the filter 808 to determine whether the speech content of the filter output includes a wake word. In some embodiments, the speech processing block 810 is implemented as software executed by one or more processors of the network device 700. In other embodiments, the speech processing block 810 is a separate computing system, such as one or more of computing devices 504, 506, and/or 508 shown and described with reference to FIG. 5.

In response to determining that the output of the filter 808 includes a wake word, the speech processing block 810 performs further speech processing of the output of the filter 808 to identify a voice command after the wake word. And responsive to the speech processing block 810 identifying a voice command after the wake word, the network device 700 carries out a task corresponding to the identified voice command. For example, as described above, in certain embodiments the network device 700 may transmit the voice input or a portion thereof to a remote computing device associated with, e.g., a voice assistant service.

In some embodiments, the robustness and performance of the MCWF may be enhanced based on one or more of the following adjustments to the foregoing algorithm.

- 1) The parameter β can be time-frequency dependent. There are various approaches to design a time-frequency dependent β depending on the speech presence probability, signal-to-diffuse ratio (SDR), etc. The idea is to use small values when the SDR is high and speech is present to reduce speech distortion, and use larger values when the SDR is low or speech is not present to increase noise reduction. This value provides a trade-off between noise reduction and speech distortion based on the conditional speech presence probability. A simple and effective approach is to define β as:
  
  β(y)=β₀(α_β+(1−α_β)β₀P(H1|y)
  
  where the conditional speech presence probability is incorporated to adapt the parameter β based on the input vector y. The parameter α_β provides a compromise between a fixed tuning parameter and one purely dependent on probability of speech presence. In one implementation α_β=0.5.
- 2) The MMSE estimate of the desired speech signal can be obtained according to
  
  y_out=P(H₁|Y)H^H(n)y(n)+(1−P(H₁|y))G_miny
  
  where the gain factor G_mindetermines the maximum amount of noise reduction when the speech presence probability indicates that speech is not present. The importance of this model is that it mitigates speech distortions in case of a false decision on speech presence probability. This approach improves the robustness. The implementation can be done after step 13 of the algorithm, y_ourcan be modified as
  
  y_out=P(H₁|y)y_out+(1−P(H₁|y))G_miny
  
  where speech presence probability is utilized to generate the output and also controls how G_minis being applied.
- 3) The algorithm is tuned and implemented in two supported modes. A) Noise Suppression (NS), B) Residual Echo Suppression (RES). If the speaker is playing content, the algorithm can be run in RES mode. Otherwise, the algorithm is run in NS mode. The mode can be determined using the internal state about existence of audio playback.
- 4) Initialization of covariance matrices in step 1 of the algorithm. The algorithm incorporates an initialization period where the input signal to the microphone array is used to estimate the initial input and noise covariance matrices. That can be assumed during this initialization period, speech is not present. These covariance matrices are initialized with diagonal matrices to simplify the implementation. The initialization time can be adjusted in the algorithm, such as to 0.5 second. This method provides a more robust solution which is not sensitive to input levels and noise type. As a result, relatively very similar convergence speeds across all SNR levels and loudness levels can be achieved.
- 5) In order to improve the multi-channel speech presence probability taking into account the statistical characteristics of the speech signal, one can use the recursively smoothed multi-channel speech presence probability as follows
  
  P(n)=α_PP(n−1)+(1−α_p)P(H₁|y),
  
  where the smoothing coefficient α_pis a value between 0 and 1, and can be adjusted to tune the estimation of speech presence probability during the parameter tuning stage.

V. Example Noise Suppression Methods

FIG. 9 shows an example embodiment of a method 900 that can be implemented by a network device, such as network device 700 or any of the PBDs, NMDs, controller devices, or other VEDs disclosed and/or described herein, or any other voice-enabled device now known or later developed.

Various embodiments of method 900 include one or more operations, functions, and actions illustrated by blocks 902 through 914. Although the blocks are illustrated in sequential order, these blocks may also be performed in parallel, and/or in a different order than the order disclosed and described herein. Also, the various blocks may be combined into fewer blocks, divided into additional blocks, and/or removed based upon a desired implementation.

In addition, for the method 900 and other processes and methods disclosed herein, the flowchart shows functionality and operation of one possible implementation of some embodiments. In this regard, each block may represent a module, a segment, or a portion of program code, which includes one or more instructions executable by one or more processors for implementing specific logical functions or steps in the process. The program code may be stored on any type of computer readable medium, for example, such as a storage device including a disk or hard drive. The computer readable medium may include non-transitory computer readable media, for example, such as tangible, non-transitory computer-readable media that stores data for short periods of time like register memory, processor cache, and Random Access Memory (RAM). The computer readable medium may also include non-transitory media, such as secondary or persistent long term storage, like read only memory (ROM), optical or magnetic disks, compact-disc read only memory (CD-ROM), for example. The computer readable media may also be any other volatile or non-volatile storage systems. The computer readable medium may be considered a computer readable storage medium, for example, or a tangible storage device. In addition, for the method 800 and other processes and methods disclosed herein, each block in FIG. 9 may represent circuitry that is wired to perform the specific logical functions in the process.

Method 900 begins at block 902, which includes a network device capturing (i) a first audio signal via a first microphone of a plurality of microphones and (ii) a second audio signal via a second microphone of the plurality of microphones, where the first audio signal includes first noise content from a noise source and the second audio signal includes second noise content from that same noise source. In some embodiments, the plurality of microphones, including the first and second microphones, are components of the same network device, such as network devices 700a or 700b depicted in FIGS. 7A-B. In other embodiments, at least some microphones of the plurality of microphones are components of different network devices, for example, as depicted in FIG. 7C. In an example implementation, the first microphone is a component of a first network device, such as network device 700c, and the second microphone is a component of a second network device, such as network device 700d.

Next, method 900 advances to block 904, which includes identifying the first noise content in the first audio signal. In some embodiments, the step of identifying the first noise content in the first audio signal involves one or more of: (i) the network device using a VAD algorithm to detect that speech is not present in the first audio signal or (ii) the network device using a speech presence probability algorithm to determine a probability that speech is present in the first audio signal. An example of a speech presence probability algorithm is described above with respect to Equation 18. If the VAD algorithm detects that speech is not present in the first audio signal or if the speech presence probability algorithm indicates that the probability of speech being present in the first audio signal is below a threshold probability, then this can suggest that the first audio signal is noise-dominant and includes little or no speech content.

Next, method 900 advances to block 906, which includes using the identified first noise content to determine an estimated noise content captured by the plurality of microphones. In some embodiments, the step of using the identified first noise content to determine an estimated noise content captured by the plurality of microphones involves the network device updating a noise content PSD matrix for use in the MCWF algorithm described above with respect to Equations 30-34.

In some embodiments, the steps of identifying the first noise content in the first audio signal at block 904 and using the identified first noise content to determine an estimated noise content captured by the plurality of microphones at block 906 are carried out based on the probability of speech being present in the first audio signal being below a threshold probability. As noted above, the speech presence probability algorithm indicating that the probability of speech being present in the first audio signal is below the threshold probability suggests that the first audio signal is noise-dominant and includes little or no speech content. Such a noise-dominant signal is more likely than less noise-dominant signals to provide an accurate estimate of noise present in other signals captured by the microphones, such as the second audio signal. Accordingly, in some embodiments, the step of using the identified first noise content to determine an estimated noise content captured by the plurality of microphones is carried out responsive to determining that the probability of speech being present in the first audio signal is below the threshold probability. The threshold probability can take on various values and, in some embodiments, can be adjusted to tune the noise filtering methods described herein. In some embodiments, the threshold probability is set as low as 1%. In other embodiments, the threshold probability is set to a higher value, such as between 1% and 10%.

Next, method 900 advances to block 908, which includes using the estimated noise content to suppress the first noise content in the first audio signal and the second noise content in the second audio signal. In some embodiments, the step of using the estimated noise content to suppress the first noise content in the first audio signal and the second noise content in the second audio signal involves the network device using the updated noise content PSD matrix to apply a linear filter to each audio signal captured by the plurality of microphones, as described above with respect to Equations 35-40.

Next, method 900 advances to block 910, which includes combining the suppressed first audio signal and the suppressed second audio signal into a third audio signal. In some embodiments, the step of combining the suppressed first audio signal and the suppressed second audio signal into a third audio signal involves the network device combining suppressed audio signals from all microphones of the plurality of microphones into the third audio signal.

Next, method 900 advances to block 912, which includes determining that the third audio signal includes a voice input comprising a wake word. In some embodiments, the step of determining that the third audio signal includes a voice input comprising a wake word involves the network device performing one or more voice processing algorithms on the third audio signal to determine whether any portion of the third audio signal includes a wake word. In operation, the step of determining that the third audio signal includes a voice input comprising a wake word can be performed according to any of the wake word detection methods disclosed and described herein and/or any wake word detection method now known or later developed.

Finally, method 900 advances to block 914, which includes, in response to the determination that the third audio signal includes speech content comprising a wake word, transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word. As noted above, the voice input may include the wake word as well as a voice utterance that follows the wake word. The voice utterance may include a spoken command as well as one or more spoken keywords. Accordingly, in some embodiments, the step of transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word comprises transmitting a portion of the voice input after the wake word, which may include the spoken command and/or the spoken keywords, to a separate computing system for voice analysis.

VII. Conclusion

The description above discloses, among other things, various example systems, methods, apparatus, and articles of manufacture including, among other components, firmware and/or software executed on hardware. It is understood that such examples are merely illustrative and should not be considered as limiting. For example, it is contemplated that any or all of the firmware, hardware, and/or software aspects or components can be embodied exclusively in hardware, exclusively in software, exclusively in firmware, or in any combination of hardware, software, and/or firmware. Accordingly, the examples provided are not the only way(s) to implement such systems, methods, apparatus, and/or articles of manufacture.

Additionally, references herein to “embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one example embodiment of an invention. The appearances of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. As such, the embodiments described herein, explicitly and implicitly understood by one skilled in the art, can be combined with other embodiments.

The specification is presented largely in terms of illustrative environments, systems, procedures, steps, logic blocks, processing, and other symbolic representations that directly or indirectly resemble the operations of data processing devices coupled to networks. These process descriptions and representations are typically used by those skilled in the art to most effectively convey the substance of their work to others skilled in the art. Numerous specific details are set forth to provide a thorough understanding of the present disclosure. However, it is understood to those skilled in the art that certain embodiments of the present disclosure can be practiced without certain, specific details. In other instances, well known methods, procedures, components, and circuitry have not been described in detail to avoid unnecessarily obscuring aspects of the embodiments. For example, in some embodiments other techniques for determining the probability of speech absence may be employed. Accordingly, the scope of the present disclosure is defined by the appended claims rather than the forgoing description of embodiments.

When any of the appended claims are read to cover a purely software and/or firmware implementation, at least one of the elements in at least one example is hereby expressly defined to include a tangible, non-transitory medium such as a computer memory, DVD, CD, Blu-ray, and so on, storing the software and/or firmware.

Claims

1. A network device comprising: a plurality of microphones comprising a first microphone and a second microphone;one or more processors; andtangible, non-transitory, computer-readable media storing instructions executable by the one or more processors to cause the network device to perform operations comprising: capturing (i) a first audio signal via the first microphone and (ii) a second audio signal via the second microphone, wherein the first audio signal comprises first noise content from a noise source and the second audio signal comprises second noise content from the noise source;identifying the first noise content in the first audio signal;using the identified first noise content to determine an estimated noise content captured by the plurality of microphones;using the estimated noise content to suppress the first noise content in the first audio signal and the second noise content in the second audio signal;combining the suppressed first audio signal and the suppressed second audio signal into a third audio signal;determining that the third audio signal includes a voice input comprising a wake word; andin response to the determination, transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word.
2. The network device of claim 1, the operations further comprising: determining a probability that the first audio signal comprises speech content,wherein the steps of (i) identifying the first noise content in the first audio signal and (ii) using the identified first noise content to determine an estimated noise content captured by the plurality of microphones are carried out based on the determined probability being below a threshold probability.
3. The network device of claim 1 further comprising a housing that at least partially encloses components of the network device within the housing, wherein the first and second microphones are disposed along the housing and separated from one another by a distance that is greater than about five centimeters.
4. The network device of claim 1, the operations further comprising: capturing a fourth audio signal via a third microphone of the plurality of microphones, wherein the fourth audio signal comprises third noise content from the noise source;identifying the third noise content in the fourth audio signal; andusing the identified third noise content to update the estimated noise content captured by the plurality of microphones.
5. The network device of claim 4, wherein the network device captures the fourth audio signal concurrently with capturing the first and second audio signals.
6. The network device of claim 4, further comprising a housing that at least partially encloses components of the network device within the housing, wherein the first, second, and third microphones are disposed along the housing and separated from one another by a distance that is greater than about five centimeters.
7. The network device of claim 1, wherein transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word comprises transmitting a portion of the voice input after the wake word to a separate computing system for voice analysis.
8. Tangible, non-transitory, computer-readable media storing instructions executable by one or more processors to cause a network device to perform operations comprising: capturing, via a plurality of microphones of a network device, (i) a first audio signal via a first microphone of the plurality of microphones and (ii) a second audio signal via a second microphone of the plurality of microphones, wherein the first audio signal comprises first noise content from a noise source and the second audio signal comprises second noise content from the noise source;identifying the first noise content in the first audio signal;using the identified first noise content to determine an estimated noise content captured by the plurality of microphones;using the estimated noise content to suppress the first noise content in the first audio signal and the second noise content in the second audio signal;combining the suppressed first audio signal and the suppressed second audio signal into a third audio signal;determining that the third audio signal includes a voice input comprising a wake word; andin response to the determination, transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word.
9. The tangible, non-transitory, computer-readable media of claim 8, the operations further comprising: determining a probability that the first audio signal comprises speech content,wherein the steps of (i) identifying the first noise content in the first audio signal and (ii) using the identified first noise content to determine an estimated noise content captured by the plurality of microphones are carried out based on the determined probability being below a threshold probability.
10. The tangible, non-transitory, computer-readable media of claim 8, wherein the network device comprises a housing that at least partially encloses components of the network device within the housing, and wherein the first and second microphones are disposed along the housing and separated from one another by a distance that is greater than about five centimeters.
11. The tangible, non-transitory, computer-readable media of claim 8, the operations further comprising: capturing a fourth audio signal via a third microphone of the plurality of microphones, wherein the fourth audio signal comprises third noise content from the noise source;identifying the third noise content in the fourth audio signal; andusing the identified third noise content to update the estimated noise content captured by the plurality of microphones.
12. The tangible, non-transitory, computer-readable media of claim 11, wherein the fourth audio signal is captured concurrently with the first and second audio signals.
13. The tangible, non-transitory, computer-readable media of claim 11, wherein the network device comprises a housing that at least partially encloses components of the network device within the housing, wherein the first, second, and third microphones are disposed along the housing and separated from one another by a distance that is greater than about five centimeters.
14. The tangible, non-transitory, computer-readable media of claim 8, wherein transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word comprises transmitting a portion of the voice input after the wake word to a separate computing system for voice analysis.
15. A method comprising: capturing, via a plurality of microphones of a network device, (i) a first audio signal via a first microphone of the plurality of microphones and (ii) a second audio signal via a second microphone of the plurality of microphones, wherein the first audio signal comprises first noise content from a noise source and the second audio signal comprises second noise content from the noise source;identifying the first noise content in the first audio signal;using the identified first noise content to determine an estimated noise content captured by the plurality of microphones;using the estimated noise content to suppress the first noise content in the first audio signal and the second noise content in the second audio signal;combining the suppressed first audio signal and the suppressed second audio signal into a third audio signal;determining that the third audio signal includes a voice input comprising a wake word; andin response to the determination, transmitting at least a portion of the voice input to a remote computing device for voice processing to identify a voice utterance different from the wake word.
16. The method of claim 15, further comprising: determining a probability that the first audio signal comprises speech content,wherein the steps of (i) identifying the first noise content in the first audio signal and (ii) using the identified first noise content to determine an estimated noise content captured by the plurality of microphones are carried out based on the determined probability being below a threshold probability.
17. The method of claim 15, wherein the network device comprises a housing that at least partially encloses components of the network device within the housing, and wherein the first and second microphones are disposed along the housing and separated from one another by a distance that is greater than about five centimeters.
18. The method of claim 15, further comprising: capturing a fourth audio signal via a third microphone of the plurality of microphones, wherein the fourth audio signal comprises third noise content from the noise source;identifying the third noise content in the fourth audio signal; andusing the identified third noise content to update the estimated noise content captured by the plurality of microphones.
19. The method of claim 18, wherein the fourth audio signal is captured concurrently with the first and second audio signals.
20. The method of claim 18, wherein the network device comprises a housing that at least partially encloses components of the network device within the housing, wherein the first, second, and third microphones are disposed along the housing and separated from one another by a distance that is greater than about five centimeters.

US Referenced Citations (647)

Number	Name	Date	Kind
4741038	Elko et al.	Apr 1988	A
4941187	Slater	Jul 1990	A
4974213	Siwecki	Nov 1990	A
5036538	Oken et al.	Jul 1991	A
5440644	Farinelli et al.	Aug 1995	A
5588065	Tanaka et al.	Dec 1996	A
5740260	Odom	Apr 1998	A
5761320	Farinelli et al.	Jun 1998	A
5923902	Inagaki	Jul 1999	A
5949414	Namikata et al.	Sep 1999	A
6032202	Lea et al.	Feb 2000	A
6088459	Hobelsberger	Jul 2000	A
6256554	DiLorenzo	Jul 2001	B1
6301603	Maher et al.	Oct 2001	B1
6311157	Strong	Oct 2001	B1
6404811	Cvetko et al.	Jun 2002	B1
6408078	Hobelsberger	Jun 2002	B1
6469633	Wachter	Oct 2002	B1
6522886	Youngs et al.	Feb 2003	B1
6594347	Calder et al.	Jul 2003	B1
6594630	Zlokarnik et al.	Jul 2003	B1
6611537	Edens et al.	Aug 2003	B1
6611604	Irby et al.	Aug 2003	B1
6631410	Kowalski et al.	Oct 2003	B1
6757517	Chang	Jun 2004	B2
6778869	Champion	Aug 2004	B2
7130608	Hollstrom et al.	Oct 2006	B2
7130616	Janik	Oct 2006	B2
7143939	Henzerling	Dec 2006	B2
7236773	Thomas	Jun 2007	B2
7295548	Blank et al.	Nov 2007	B2
7356471	Ito et al.	Apr 2008	B2
7391791	Balassanian et al.	Jun 2008	B2
7483538	McCarty et al.	Jan 2009	B2
7571014	Lambourne et al.	Aug 2009	B1
7630501	Blank et al.	Dec 2009	B2
7643894	Braithwaite et al.	Jan 2010	B2
7657910	McAulay et al.	Feb 2010	B1
7661107	Van et al.	Feb 2010	B1
7702508	Bennett	Apr 2010	B2
7792311	Holmgren et al.	Sep 2010	B1
7853341	McCarty et al.	Dec 2010	B2
7961892	Fedigan	Jun 2011	B2
7987294	Bryce et al.	Jul 2011	B2
8014423	Thaler et al.	Sep 2011	B2
8032383	Bhardwaj et al.	Oct 2011	B1
8041565	Bhardwaj et al.	Oct 2011	B1
8045952	Qureshey et al.	Oct 2011	B2
8073125	Zhang et al.	Dec 2011	B2
8073681	Baldwin et al.	Dec 2011	B2
8103009	McCarty et al.	Jan 2012	B2
8136040	Fleming	Mar 2012	B2
8234395	Millington et al.	Jul 2012	B2
8239206	Lebeau et al.	Aug 2012	B1
8255224	Singleton et al.	Aug 2012	B2
8284982	Bailey	Oct 2012	B2
8290603	Lambourne	Oct 2012	B1
8340975	Rosenberger	Dec 2012	B1
8364481	Strope et al.	Jan 2013	B2
8385557	Tashev et al.	Feb 2013	B2
8386261	Mellott et al.	Feb 2013	B2
8423893	Ramsay et al.	Apr 2013	B2
8428758	Naik et al.	Apr 2013	B2
8453058	Coccaro et al.	May 2013	B1
8473618	Spear et al.	Jun 2013	B2
8483853	Lambourne	Jul 2013	B1
8484025	Moreno et al.	Jul 2013	B1
8738925	Park et al.	May 2014	B1
8831761	Kemp et al.	Sep 2014	B2
8831957	Taubman et al.	Sep 2014	B2
8848879	Coughlan et al.	Sep 2014	B1
8874448	Kauffmann et al.	Oct 2014	B1
8938394	Faaborg et al.	Jan 2015	B1
8942252	Balassanian et al.	Jan 2015	B2
8983383	Haskin	Mar 2015	B1
8983844	Thomas et al.	Mar 2015	B1
9015049	Baldwin et al.	Apr 2015	B2
9042556	Kallai et al.	May 2015	B2
9060224	List	Jun 2015	B1
9094539	Noble	Jul 2015	B1
9215545	Dublin et al.	Dec 2015	B2
9251793	Lebeau et al.	Feb 2016	B2
9253572	Bedingfield, Sr. et al.	Feb 2016	B2
9262612	Cheyer	Feb 2016	B2
9275637	Salvador et al.	Mar 2016	B1
9288597	Carlsson et al.	Mar 2016	B2
9300266	Grokop	Mar 2016	B2
9304736	Whiteley et al.	Apr 2016	B1
9307321	Unruh	Apr 2016	B1
9318107	Sharifi	Apr 2016	B1
9319816	Narayanan	Apr 2016	B1
9324322	Torok et al.	Apr 2016	B1
9335819	Jaeger et al.	May 2016	B1
9361878	Boukadakis	Jun 2016	B2
9368105	Freed et al.	Jun 2016	B1
9374634	Macours	Jun 2016	B2
9386154	Baciu et al.	Jul 2016	B2
9401058	De La Fuente et al.	Jul 2016	B2
9412392	Lindahl et al.	Aug 2016	B2
9426567	Lee et al.	Aug 2016	B2
9431021	Scalise et al.	Aug 2016	B1
9443527	Watanabe et al.	Sep 2016	B1
9472201	Sleator	Oct 2016	B1
9472203	Ayrapetian et al.	Oct 2016	B1
9484030	Meaney et al.	Nov 2016	B1
9489948	Chu et al.	Nov 2016	B1
9494683	Sadek	Nov 2016	B1
9509269	Rosenberg	Nov 2016	B1
9510101	Polleros	Nov 2016	B1
9514476	Kay et al.	Dec 2016	B2
9514752	Sharifi	Dec 2016	B2
9516081	Tebbs et al.	Dec 2016	B2
9536541	Chen et al.	Jan 2017	B2
9548053	Basye et al.	Jan 2017	B1
9548066	Jain et al.	Jan 2017	B2
9552816	Vanlund et al.	Jan 2017	B2
9554210	Ayrapetian et al.	Jan 2017	B1
9560441	Mcdonough, Jr. et al.	Jan 2017	B1
9576591	Kim et al.	Feb 2017	B2
9601116	Casado et al.	Mar 2017	B2
9615170	Kirsch et al.	Apr 2017	B2
9615171	O'Neill et al.	Apr 2017	B1
9626695	Balasubramanian et al.	Apr 2017	B2
9632748	Faaborg et al.	Apr 2017	B2
9633186	Ingrassia, Jr. et al.	Apr 2017	B2
9633368	Greenzeiger et al.	Apr 2017	B2
9633660	Haughay et al.	Apr 2017	B2
9633671	Giacobello et al.	Apr 2017	B2
9633674	Sinha et al.	Apr 2017	B2
9640179	Hart et al.	May 2017	B1
9640183	Jung et al.	May 2017	B2
9641919	Poole et al.	May 2017	B1
9646614	Bellegarda et al.	May 2017	B2
9653060	Hilmes et al.	May 2017	B1
9653075	Chen et al.	May 2017	B1
9659555	Hilmes et al.	May 2017	B1
9672821	Krishnaswamy et al.	Jun 2017	B2
9685171	Yang	Jun 2017	B1
9691378	Meyers et al.	Jun 2017	B1
9691379	Mathias et al.	Jun 2017	B1
9697826	Sainath et al.	Jul 2017	B2
9697828	Prasad et al.	Jul 2017	B1
9698999	Mutagi et al.	Jul 2017	B2
9704478	Vitaladevuni et al.	Jul 2017	B1
9721566	Newendorp et al.	Aug 2017	B2
9721568	Polansky et al.	Aug 2017	B1
9721570	Beal et al.	Aug 2017	B1
9728188	Rosen et al.	Aug 2017	B1
9734822	Sundaram et al.	Aug 2017	B1
9743204	Welch et al.	Aug 2017	B1
9747011	Lewis et al.	Aug 2017	B2
9747899	Pogue et al.	Aug 2017	B2
9747920	Ayrapetian et al.	Aug 2017	B2
9747926	Sharifi et al.	Aug 2017	B2
9754605	Chhetri	Sep 2017	B1
9762967	Clarke et al.	Sep 2017	B2
9769420	Moses	Sep 2017	B1
9811314	Plagge et al.	Nov 2017	B2
9813810	Nongpiur	Nov 2017	B1
9813812	Berthelsen et al.	Nov 2017	B2
9820036	Tritschler et al.	Nov 2017	B1
9820039	Lang	Nov 2017	B2
9826306	Lang	Nov 2017	B2
9865259	Typrin et al.	Jan 2018	B1
9865264	Gelfenbeyn et al.	Jan 2018	B2
9881616	Beckley et al.	Jan 2018	B2
9900723	Choisel et al.	Feb 2018	B1
9916839	Scalise et al.	Mar 2018	B1
9947316	Millington et al.	Apr 2018	B2
9947333	David	Apr 2018	B1
9972318	Kelly et al.	May 2018	B1
9973849	Zhang et al.	May 2018	B1
10013995	Lashkari et al.	Jul 2018	B1
10026401	Mutagi et al.	Jul 2018	B1
10048930	Vega et al.	Aug 2018	B1
10049675	Haughay	Aug 2018	B2
10051366	Buoni et al.	Aug 2018	B1
10051600	Zhong et al.	Aug 2018	B1
10068573	Aykac et al.	Sep 2018	B1
10074371	Wang et al.	Sep 2018	B1
10079015	Lockhart et al.	Sep 2018	B1
10116748	Farmer et al.	Oct 2018	B2
10134399	Lang et al.	Nov 2018	B2
10136204	Poole et al.	Nov 2018	B1
10152969	Reilly et al.	Dec 2018	B2
10224056	Torok et al.	Mar 2019	B1
10276161	Hughes et al.	Apr 2019	B2
10297256	Reilly et al.	May 2019	B2
10339917	Aleksic et al.	Jul 2019	B2
10346122	Morgan	Jul 2019	B1
10354650	Gruenstein et al.	Jul 2019	B2
10366688	Gunn et al.	Jul 2019	B2
10374816	Leblang et al.	Aug 2019	B1
10381001	Gunn et al.	Aug 2019	B2
10381002	Gunn et al.	Aug 2019	B2
10381003	Wakisaka et al.	Aug 2019	B2
10445057	Vega et al.	Oct 2019	B2
10499146	Lang et al.	Dec 2019	B2
10511904	Buoni et al.	Dec 2019	B2
10546583	White et al.	Jan 2020	B2
10602268	Soto	Mar 2020	B1
10624612	Sumi et al.	Apr 2020	B2
20010042107	Palm	Nov 2001	A1
20020022453	Balog et al.	Feb 2002	A1
20020026442	Lipscomb et al.	Feb 2002	A1
20020034280	Infosino	Mar 2002	A1
20020072816	Shdema et al.	Jun 2002	A1
20020116196	Tran	Aug 2002	A1
20020124097	Isely et al.	Sep 2002	A1
20030038848	Lee et al.	Feb 2003	A1
20030040908	Yang et al.	Feb 2003	A1
20030070869	Hlibowicki	Apr 2003	A1
20030072462	Hlibowicki	Apr 2003	A1
20030095672	Hobelsberger	May 2003	A1
20030157951	Hasty	Aug 2003	A1
20040024478	Hans et al.	Feb 2004	A1
20040093219	Shin et al.	May 2004	A1
20040127241	Shostak	Jul 2004	A1
20040128135	Anastasakos et al.	Jul 2004	A1
20040234088	McCarty et al.	Nov 2004	A1
20050031131	Browning et al.	Feb 2005	A1
20050031132	Browning et al.	Feb 2005	A1
20050031133	Browning et al.	Feb 2005	A1
20050031134	Leske	Feb 2005	A1
20050031137	Browning et al.	Feb 2005	A1
20050031138	Browning et al.	Feb 2005	A1
20050031139	Browning et al.	Feb 2005	A1
20050031140	Browning	Feb 2005	A1
20050047606	Lee et al.	Mar 2005	A1
20050077843	Benditt	Apr 2005	A1
20050164664	Difonzo et al.	Jul 2005	A1
20050195988	Tashev	Sep 2005	A1
20050201254	Looney et al.	Sep 2005	A1
20050207584	Bright	Sep 2005	A1
20050268234	Rossi et al.	Dec 2005	A1
20050283330	Laraia et al.	Dec 2005	A1
20060004834	Pyhalammi et al.	Jan 2006	A1
20060023945	King et al.	Feb 2006	A1
20060104451	Browning et al.	May 2006	A1
20060147058	Wang	Jul 2006	A1
20060190269	Tessel et al.	Aug 2006	A1
20060190968	Jung et al.	Aug 2006	A1
20060247913	Huerta et al.	Nov 2006	A1
20060262943	Oxford	Nov 2006	A1
20070018844	Sutardja	Jan 2007	A1
20070019815	Asada et al.	Jan 2007	A1
20070033043	Hyakumoto	Feb 2007	A1
20070071255	Schobben	Mar 2007	A1
20070076131	Li et al.	Apr 2007	A1
20070076906	Takagi et al.	Apr 2007	A1
20070140058	McIntosh et al.	Jun 2007	A1
20070140521	Mitobe et al.	Jun 2007	A1
20070142944	Goldberg et al.	Jun 2007	A1
20070147651	Mitobe et al.	Jun 2007	A1
20080037814	Shau	Feb 2008	A1
20080090537	Sutardja	Apr 2008	A1
20080146289	Korneluk et al.	Jun 2008	A1
20080182518	Lo	Jul 2008	A1
20080208594	Cross et al.	Aug 2008	A1
20080221897	Cerra et al.	Sep 2008	A1
20080247530	Barton et al.	Oct 2008	A1
20080248797	Freeman et al.	Oct 2008	A1
20080291896	Tuubel et al.	Nov 2008	A1
20080301729	Broos et al.	Dec 2008	A1
20090003620	McKillop et al.	Jan 2009	A1
20090005893	Sugii et al.	Jan 2009	A1
20090010445	Matsuo	Jan 2009	A1
20090018828	Nakadai et al.	Jan 2009	A1
20090043206	Towfiq et al.	Feb 2009	A1
20090052688	Ishibashi et al.	Feb 2009	A1
20090076821	Brenner et al.	Mar 2009	A1
20090153289	Hope et al.	Jun 2009	A1
20090197524	Haff et al.	Aug 2009	A1
20090220107	Every et al.	Sep 2009	A1
20090228919	Zott et al.	Sep 2009	A1
20090238377	Ramakrishnan et al.	Sep 2009	A1
20090248397	Garcia et al.	Oct 2009	A1
20090264072	Dai	Oct 2009	A1
20090323907	Gupta et al.	Dec 2009	A1
20090326949	Douthitt et al.	Dec 2009	A1
20100014690	Wolff	Jan 2010	A1
20100023638	Bowman	Jan 2010	A1
20100035593	Franco et al.	Feb 2010	A1
20100070922	Demaio et al.	Mar 2010	A1
20100075723	Min et al.	Mar 2010	A1
20100088100	Lindahl	Apr 2010	A1
20100092004	Kuze	Apr 2010	A1
20100172516	Lastrucci	Jul 2010	A1
20100178873	Lee et al.	Jul 2010	A1
20100179874	Higgins et al.	Jul 2010	A1
20100185448	Meisel	Jul 2010	A1
20100211199	Naik et al.	Aug 2010	A1
20110033059	Bhaskar et al.	Feb 2011	A1
20110035580	Wang et al.	Feb 2011	A1
20110044461	Kuech et al.	Feb 2011	A1
20110044489	Saiki et al.	Feb 2011	A1
20110066634	Phillips et al.	Mar 2011	A1
20110091055	Leblanc	Apr 2011	A1
20110103615	Sun	May 2011	A1
20110145581	Malhotra et al.	Jun 2011	A1
20110170707	Yamada	Jul 2011	A1
20110182436	Murgia et al.	Jul 2011	A1
20110202924	Banguero et al.	Aug 2011	A1
20110267985	Wilkinson et al.	Nov 2011	A1
20110276333	Wang et al.	Nov 2011	A1
20110280422	Neumeyer et al.	Nov 2011	A1
20110289506	Trivi et al.	Nov 2011	A1
20110299706	Sakai	Dec 2011	A1
20120020486	Fried et al.	Jan 2012	A1
20120022863	Cho et al.	Jan 2012	A1
20120022864	Leman et al.	Jan 2012	A1
20120078635	Rothkopf et al.	Mar 2012	A1
20120086568	Scott et al.	Apr 2012	A1
20120123268	Tanaka et al.	May 2012	A1
20120128160	Kim et al.	May 2012	A1
20120131125	Seidel et al.	May 2012	A1
20120148075	Goh et al.	Jun 2012	A1
20120163603	Abe et al.	Jun 2012	A1
20120177215	Bose et al.	Jul 2012	A1
20120183149	Hiroe	Jul 2012	A1
20120297284	Matthews, III et al.	Nov 2012	A1
20120308044	Vander et al.	Dec 2012	A1
20120308046	Muza	Dec 2012	A1
20130006453	Wang et al.	Jan 2013	A1
20130024018	Chang et al.	Jan 2013	A1
20130034241	Pandey et al.	Feb 2013	A1
20130039527	Jensen et al.	Feb 2013	A1
20130058492	Silzle et al.	Mar 2013	A1
20130066453	Seefeldt	Mar 2013	A1
20130080146	Kato et al.	Mar 2013	A1
20130124211	McDonough	May 2013	A1
20130148821	Sorensen	Jun 2013	A1
20130179173	Lee et al.	Jul 2013	A1
20130183944	Mozer et al.	Jul 2013	A1
20130191119	Sugiyama	Jul 2013	A1
20130191122	Mason	Jul 2013	A1
20130198298	Li et al.	Aug 2013	A1
20130211826	Mannby	Aug 2013	A1
20130216056	Thyssen	Aug 2013	A1
20130262101	Srinivasan	Oct 2013	A1
20130315420	You	Nov 2013	A1
20130317635	Bates et al.	Nov 2013	A1
20130322665	Bennett et al.	Dec 2013	A1
20130324031	Loureiro	Dec 2013	A1
20130329896	Krishnaswamy	Dec 2013	A1
20130331970	Beckhardt et al.	Dec 2013	A1
20130332165	Beckley et al.	Dec 2013	A1
20130339028	Rosner et al.	Dec 2013	A1
20130343567	Triplett et al.	Dec 2013	A1
20140003611	Mohammad et al.	Jan 2014	A1
20140003625	Sheen et al.	Jan 2014	A1
20140003635	Mohammad	Jan 2014	A1
20140005813	Reimann	Jan 2014	A1
20140006026	Lamb et al.	Jan 2014	A1
20140034929	Hamada et al.	Feb 2014	A1
20140046464	Reimann	Feb 2014	A1
20140064501	Olsen et al.	Mar 2014	A1
20140075306	Rega	Mar 2014	A1
20140075311	Boettcher et al.	Mar 2014	A1
20140094151	Klappert et al.	Apr 2014	A1
20140100854	Chen et al.	Apr 2014	A1
20140122075	Bak et al.	May 2014	A1
20140136195	Abdossalami et al.	May 2014	A1
20140145168	Ohsawa et al.	May 2014	A1
20140146983	Kim et al.	May 2014	A1
20140163978	Basye et al.	Jun 2014	A1
20140164400	Kruglick	Jun 2014	A1
20140167931	Lee et al.	Jun 2014	A1
20140168344	Shoemake et al.	Jun 2014	A1
20140172953	Blanksteen	Jun 2014	A1
20140195252	Gruber et al.	Jul 2014	A1
20140219472	Huang et al.	Aug 2014	A1
20140222436	Binder et al.	Aug 2014	A1
20140244013	Reilly	Aug 2014	A1
20140244712	Walters et al.	Aug 2014	A1
20140249817	Hart et al.	Sep 2014	A1
20140252386	Ito et al.	Sep 2014	A1
20140254805	Su et al.	Sep 2014	A1
20140258292	Thramann et al.	Sep 2014	A1
20140259075	Chang et al.	Sep 2014	A1
20140270282	Tammi et al.	Sep 2014	A1
20140274185	Luna et al.	Sep 2014	A1
20140274203	Ganong, III et al.	Sep 2014	A1
20140274218	Kadiwala et al.	Sep 2014	A1
20140277650	Zurek et al.	Sep 2014	A1
20140291642	Watabe et al.	Oct 2014	A1
20140310002	Nitz et al.	Oct 2014	A1
20140310614	Jones	Oct 2014	A1
20140340888	Ishisone et al.	Nov 2014	A1
20140357248	Tonshal et al.	Dec 2014	A1
20140363022	Dizon et al.	Dec 2014	A1
20140363024	Apodaca	Dec 2014	A1
20140365227	Cash et al.	Dec 2014	A1
20140369491	Kloberdans et al.	Dec 2014	A1
20140372109	Iyer et al.	Dec 2014	A1
20150006176	Pogue et al.	Jan 2015	A1
20150006184	Marti et al.	Jan 2015	A1
20150010169	Popova et al.	Jan 2015	A1
20150014680	Yamazaki et al.	Jan 2015	A1
20150016642	Walsh et al.	Jan 2015	A1
20150019201	Schoenbach	Jan 2015	A1
20150019219	Tzirkel-Hancock et al.	Jan 2015	A1
20150036831	Klippel	Feb 2015	A1
20150063580	Huang et al.	Mar 2015	A1
20150086034	Lombardi et al.	Mar 2015	A1
20150091709	Reichert et al.	Apr 2015	A1
20150092947	Gossain et al.	Apr 2015	A1
20150104037	Lee et al.	Apr 2015	A1
20150106085	Lindahl	Apr 2015	A1
20150110294	Chen et al.	Apr 2015	A1
20150112672	Giacobello et al.	Apr 2015	A1
20150128065	Torii et al.	May 2015	A1
20150134456	Baldwin	May 2015	A1
20150154976	Mutagi	Jun 2015	A1
20150161990	Sharifi	Jun 2015	A1
20150169279	Duga	Jun 2015	A1
20150170645	Di et al.	Jun 2015	A1
20150172843	Quan	Jun 2015	A1
20150179181	Morris et al.	Jun 2015	A1
20150180432	Gao et al.	Jun 2015	A1
20150181318	Gautama et al.	Jun 2015	A1
20150189438	Hampiholi et al.	Jul 2015	A1
20150200454	Heusdens et al.	Jul 2015	A1
20150221678	Yamazaki et al.	Aug 2015	A1
20150222563	Burns et al.	Aug 2015	A1
20150222987	Angel, Jr. et al.	Aug 2015	A1
20150228274	Leppänen et al.	Aug 2015	A1
20150228803	Koezuka et al.	Aug 2015	A1
20150237406	Ochoa	Aug 2015	A1
20150245152	Ding et al.	Aug 2015	A1
20150249889	Iyer et al.	Sep 2015	A1
20150253292	Larkin et al.	Sep 2015	A1
20150253960	Lin et al.	Sep 2015	A1
20150263174	Yamazaki et al.	Sep 2015	A1
20150271593	Sun et al.	Sep 2015	A1
20150277846	Yen et al.	Oct 2015	A1
20150280676	Holman et al.	Oct 2015	A1
20150296299	Klippel et al.	Oct 2015	A1
20150302856	Kim et al.	Oct 2015	A1
20150319529	Klippel	Nov 2015	A1
20150325267	Lee et al.	Nov 2015	A1
20150334471	Innes et al.	Nov 2015	A1
20150338917	Steiner et al.	Nov 2015	A1
20150341406	Rockefeller et al.	Nov 2015	A1
20150346845	Di et al.	Dec 2015	A1
20150348548	Piernot et al.	Dec 2015	A1
20150348551	Gruber et al.	Dec 2015	A1
20150355878	Corbin	Dec 2015	A1
20150363061	De, III et al.	Dec 2015	A1
20150363401	Chen et al.	Dec 2015	A1
20150371657	Gao	Dec 2015	A1
20150371659	Gao	Dec 2015	A1
20150371664	Bar-Or et al.	Dec 2015	A1
20150380010	Srinivasan	Dec 2015	A1
20150382047	Van Os et al.	Dec 2015	A1
20160007116	Holman	Jan 2016	A1
20160021458	Johnson et al.	Jan 2016	A1
20160026428	Morganstern et al.	Jan 2016	A1
20160029142	Isaac et al.	Jan 2016	A1
20160035321	Cho et al.	Feb 2016	A1
20160036962	Rand et al.	Feb 2016	A1
20160042748	Jain et al.	Feb 2016	A1
20160044151	Shoemaker et al.	Feb 2016	A1
20160050488	Matheja et al.	Feb 2016	A1
20160057522	Choisel et al.	Feb 2016	A1
20160077710	Lewis et al.	Mar 2016	A1
20160088036	Corbin et al.	Mar 2016	A1
20160088392	Huttunen et al.	Mar 2016	A1
20160093304	Kim et al.	Mar 2016	A1
20160094718	Mani et al.	Mar 2016	A1
20160094917	Wilk et al.	Mar 2016	A1
20160098393	Hebert	Apr 2016	A1
20160098992	Renard et al.	Apr 2016	A1
20160103653	Jang	Apr 2016	A1
20160104480	Sharifi	Apr 2016	A1
20160111110	Gautama et al.	Apr 2016	A1
20160125876	Schroeter et al.	May 2016	A1
20160127780	Roberts et al.	May 2016	A1
20160133259	Rubin et al.	May 2016	A1
20160134982	Iyer	May 2016	A1
20160154089	Altman	Jun 2016	A1
20160155442	Kannan et al.	Jun 2016	A1
20160155443	Khan et al.	Jun 2016	A1
20160157035	Russell et al.	Jun 2016	A1
20160162469	Santos	Jun 2016	A1
20160173578	Sharma et al.	Jun 2016	A1
20160173983	Berthelsen et al.	Jun 2016	A1
20160180853	Vanlund et al.	Jun 2016	A1
20160189716	Lindahl et al.	Jun 2016	A1
20160196499	Khan et al.	Jul 2016	A1
20160203331	Khan et al.	Jul 2016	A1
20160212538	Fullam et al.	Jul 2016	A1
20160216938	Millington	Jul 2016	A1
20160225385	Hammarqvist	Aug 2016	A1
20160232451	Scherzer	Aug 2016	A1
20160234204	Rishi et al.	Aug 2016	A1
20160239255	Chavez et al.	Aug 2016	A1
20160241976	Pearson	Aug 2016	A1
20160253050	Mishra et al.	Sep 2016	A1
20160260431	Newendorp et al.	Sep 2016	A1
20160302018	Russell et al.	Oct 2016	A1
20160314782	Klimanis	Oct 2016	A1
20160316293	Klimanis	Oct 2016	A1
20160336519	Seo et al.	Nov 2016	A1
20160343866	Koezuka et al.	Nov 2016	A1
20160343949	Seo et al.	Nov 2016	A1
20160343954	Seo et al.	Nov 2016	A1
20160345114	Hanna et al.	Nov 2016	A1
20160352915	Gautama	Dec 2016	A1
20160353218	Starobin et al.	Dec 2016	A1
20160357503	Triplett et al.	Dec 2016	A1
20160366515	Mendes et al.	Dec 2016	A1
20160372688	Seo et al.	Dec 2016	A1
20160373269	Okubo et al.	Dec 2016	A1
20160373909	Rasmussen et al.	Dec 2016	A1
20160379634	Yamamoto et al.	Dec 2016	A1
20170003931	Dvortsov et al.	Jan 2017	A1
20170012207	Seo et al.	Jan 2017	A1
20170012232	Kataishi et al.	Jan 2017	A1
20170019732	Mendes et al.	Jan 2017	A1
20170025615	Seo et al.	Jan 2017	A1
20170025630	Seo et al.	Jan 2017	A1
20170026769	Patel	Jan 2017	A1
20170039025	Kielak	Feb 2017	A1
20170040018	Tormey	Feb 2017	A1
20170041724	Master et al.	Feb 2017	A1
20170060526	Barton et al.	Mar 2017	A1
20170062734	Suzuki et al.	Mar 2017	A1
20170070478	Park et al.	Mar 2017	A1
20170076720	Gopalan et al.	Mar 2017	A1
20170078824	Heo	Mar 2017	A1
20170083285	Meyers et al.	Mar 2017	A1
20170084277	Sharifi	Mar 2017	A1
20170084292	Yoo	Mar 2017	A1
20170084295	Tsiartas et al.	Mar 2017	A1
20170090864	Jorgovanovic	Mar 2017	A1
20170092278	Evermann et al.	Mar 2017	A1
20170092297	Sainath et al.	Mar 2017	A1
20170092299	Matsuo	Mar 2017	A1
20170092889	Seo et al.	Mar 2017	A1
20170092890	Seo et al.	Mar 2017	A1
20170094215	Western	Mar 2017	A1
20170103754	Higbie et al.	Apr 2017	A1
20170103755	Jeon et al.	Apr 2017	A1
20170110124	Boesen et al.	Apr 2017	A1
20170110144	Sharifi et al.	Apr 2017	A1
20170117497	Seo et al.	Apr 2017	A1
20170123251	Nakada et al.	May 2017	A1
20170125037	Shin	May 2017	A1
20170125456	Kasahara	May 2017	A1
20170134872	Silva et al.	May 2017	A1
20170139720	Stein	May 2017	A1
20170140748	Roberts et al.	May 2017	A1
20170140759	Kumar et al.	May 2017	A1
20170177585	Rodger et al.	Jun 2017	A1
20170178662	Ayrapetian et al.	Jun 2017	A1
20170180561	Kadiwala et al.	Jun 2017	A1
20170188150	Brunet et al.	Jun 2017	A1
20170193999	Aleksic et al.	Jul 2017	A1
20170206896	Ko et al.	Jul 2017	A1
20170206900	Lee et al.	Jul 2017	A1
20170214996	Yeo	Jul 2017	A1
20170236512	Williams	Aug 2017	A1
20170236515	Pinsky et al.	Aug 2017	A1
20170242649	Jarvis et al.	Aug 2017	A1
20170242651	Lang et al.	Aug 2017	A1
20170242653	Lang et al.	Aug 2017	A1
20170242657	Jarvis et al.	Aug 2017	A1
20170243576	Millington et al.	Aug 2017	A1
20170243587	Plagge et al.	Aug 2017	A1
20170245076	Kusano et al.	Aug 2017	A1
20170257686	Gautama et al.	Sep 2017	A1
20170270919	Parthasarathi	Sep 2017	A1
20170287485	Civelli et al.	Oct 2017	A1
20170332168	Moghimi et al.	Nov 2017	A1
20170352357	Fink	Dec 2017	A1
20170353789	Kim	Dec 2017	A1
20170357475	Lee et al.	Dec 2017	A1
20170357478	Piersol et al.	Dec 2017	A1
20170366393	Shaker et al.	Dec 2017	A1
20170374454	Bernardini et al.	Dec 2017	A1
20180025733	Qian et al.	Jan 2018	A1
20180033428	Kim	Feb 2018	A1
20180040324	Wilberding	Feb 2018	A1
20180047394	Tian et al.	Feb 2018	A1
20180053504	Wang et al.	Feb 2018	A1
20180054506	Hart et al.	Feb 2018	A1
20180062871	Jones et al.	Mar 2018	A1
20180084367	Greff et al.	Mar 2018	A1
20180091898	Yoon et al.	Mar 2018	A1
20180091913	Hartung et al.	Mar 2018	A1
20180096683	James et al.	Apr 2018	A1
20180096696	Mixter	Apr 2018	A1
20180122378	Mixter et al.	May 2018	A1
20180130469	Gruenstein et al.	May 2018	A1
20180132217	Stirling-Gallacher	May 2018	A1
20180132298	Birnam et al.	May 2018	A1
20180137861	Ogawa	May 2018	A1
20180165055	Yu et al.	Jun 2018	A1
20180167981	Jonna et al.	Jun 2018	A1
20180190285	Heckmann et al.	Jul 2018	A1
20180199146	Sheen	Jul 2018	A1
20180210698	Park et al.	Jul 2018	A1
20180218747	Moghimi et al.	Aug 2018	A1
20180219976	Decenzo et al.	Aug 2018	A1
20180225933	Park et al.	Aug 2018	A1
20180228006	Baker et al.	Aug 2018	A1
20180233136	Torok et al.	Aug 2018	A1
20180233137	Torok et al.	Aug 2018	A1
20180233139	Finkelstein et al.	Aug 2018	A1
20180262793	Lau et al.	Sep 2018	A1
20180277107	Kim	Sep 2018	A1
20180277113	Hartung et al.	Sep 2018	A1
20180277133	Deetz et al.	Sep 2018	A1
20180293484	Wang et al.	Oct 2018	A1
20180308470	Park et al.	Oct 2018	A1
20180314552	Kim et al.	Nov 2018	A1
20180324756	Ryu et al.	Nov 2018	A1
20180335903	Coffman et al.	Nov 2018	A1
20180336274	Choudhury et al.	Nov 2018	A1
20180358009	Daley et al.	Dec 2018	A1
20180365567	Kolavennu et al.	Dec 2018	A1
20180367944	Heo et al.	Dec 2018	A1
20190013019	Lawrence	Jan 2019	A1
20190033446	Bultan et al.	Jan 2019	A1
20190043492	Lang	Feb 2019	A1
20190074025	Lashkari et al.	Mar 2019	A1
20190079724	Feuz et al.	Mar 2019	A1
20190081507	Ide	Mar 2019	A1
20190088261	Lang et al.	Mar 2019	A1
20190090056	Rexach et al.	Mar 2019	A1
20190098400	Buoni et al.	Mar 2019	A1
20190104119	Giorgi et al.	Apr 2019	A1
20190104373	Wodrich et al.	Apr 2019	A1
20190108839	Reilly et al.	Apr 2019	A1
20190130906	Kobayashi et al.	May 2019	A1
20190163153	Price et al.	May 2019	A1
20190172452	Smith et al.	Jun 2019	A1
20190173687	MacKay et al.	Jun 2019	A1
20190179607	Thangarathnam et al.	Jun 2019	A1
20190220246	Orr et al.	Jul 2019	A1
20190237067	Friedman et al.	Aug 2019	A1
20190295563	Kamdar et al.	Sep 2019	A1
20190297388	Panchaksharaiah et al.	Sep 2019	A1
20190304443	Bhagwan	Oct 2019	A1
20190311710	Eraslan et al.	Oct 2019	A1
20200034492	Verbeke et al.	Jan 2020	A1

Foreign Referenced Citations (54)

Number	Date	Country
2017100486	Jun 2017	AU
2017100581	Jun 2017	AU
101310558	Nov 2008	CN
101661753	Mar 2010	CN
102256098	Nov 2011	CN
103181192	Jun 2013	CN
103546616	Jan 2014	CN
103811007	May 2014	CN
104010251	Aug 2014	CN
104035743	Sep 2014	CN
104053088	Sep 2014	CN
104092936	Oct 2014	CN
104538030	Apr 2015	CN
104865550	Aug 2015	CN
105187907	Dec 2015	CN
105284076	Jan 2016	CN
107919123	Apr 2018	CN
1349146	Oct 2003	EP
1389853	Feb 2004	EP
2683147	Jan 2014	EP
2351021	Sep 2017	EP
3285502	Feb 2018	EP
2001236093	Aug 2001	JP
2003223188	Aug 2003	JP
2004347943	Dec 2004	JP
2004354721	Dec 2004	JP
2005284492	Oct 2005	JP
2007013400	Jan 2007	JP
2007142595	Jun 2007	JP
2008079256	Apr 2008	JP
2008158868	Jul 2008	JP
2010141748	Jun 2010	JP
2013037148	Feb 2013	JP
2014071138	Apr 2014	JP
2014137590	Jul 2014	JP
2015161551	Sep 2015	JP
20100111071	Oct 2010	KR
20130050987	May 2013	KR
20140035310	Mar 2014	KR
200153994	Jul 2001	WO
2003093950	Nov 2003	WO
2014159581	Oct 2014	WO
2015037396	Mar 2015	WO
2015178950	Nov 2015	WO
2016014142	Jan 2016	WO
2016022926	Feb 2016	WO
2016033364	Mar 2016	WO
2016057268	Apr 2016	WO
2016085775	Jun 2016	WO
2016171956	Oct 2016	WO
2017039632	Mar 2017	WO
2017138934	Aug 2017	WO
2018027142	Feb 2018	WO
2018067404	Apr 2018	WO

Non-Patent Literature Citations (274)

Entry
US 9,299,346 B1, 03/2016, Hart et al. (withdrawn)
Non-Final Office Action dated Feb. 6, 2018, issued in connection with U.S. Appl. No. 15/237,133, filed Aug. 15, 2016, 6 pages.
Non-Final Office Action dated Sep. 6, 2017, issued in connection with U.S. Appl. No. 15/131,254, filed Apr. 18, 2016, 13 pages.
Non-Final Office Action dated Apr. 9, 2018, issued in connection with U.S. Appl. No. 15/804,776, filed Nov. 6, 2017, 18 pages.
Non-Final Office Action dated May 9, 2018, issued in connection with U.S. Appl. No. 15/818,051, filed Nov. 20, 2017, 22 pages.
Notice of Allowance dated Dec. 4, 2017, issued in connection with U.S. Appl. No. 15/277,810, filed Sep. 27, 2016, 5 pages.
Notice of Allowance dated Jul. 5, 2018, issued in connection with U.S. Appl. No. 15/237,133, filed Aug. 15, 2016, 5 pages.
Notice of Allowance dated Jul. 9, 2018, issued in connection with U.S. Appl. No. 15/438,741, filed Feb. 21, 2017, 5 pages.
Notice of Allowance dated Apr. 11, 2018, issued in connection with U.S. Appl. No. 15/719,454, filed Sep. 28, 2017, 15 pages.
Notice of Allowance dated Jul. 12, 2017, issued in connection with U.S. Appl. No. 15/098,805, filed Apr. 14, 2016, 8 pages.
Notice of Allowance dated Dec. 13, 2017, issued in connection with U.S. Appl. No. 15/784,952, filed Oct. 16, 2017, 9 pages.
Notice of Allowance dated Aug. 14, 2017, issued in connection with U.S. Appl. No. 15/098,867, filed Apr. 14, 2016, 10 pages.
Notice of Allowance dated Feb. 14, 2017, issued in connection with U.S. Appl. No. 15/229,855, filed Aug. 5, 2016, 11 pages.
Notice of Allowance dated Jun. 14, 2017, issued in connection with U.S. Appl. No. 15/282,554, filed Sep. 30, 2016, 11 pages.
Notice of Allowance dated Dec. 15, 2017, issued in connection with U.S. Appl. No. 15/223,218, filed Jul. 29, 2016, 7 pages.
Notice of Allowance dated Aug. 16, 2017, issued in connection with U.S. Appl. No. 15/098,892, filed Apr. 14, 2016, 9 pages.
Notice of Allowance dated Aug. 17, 2017, issued in connection with U.S. Appl. No. 15/131,244, filed Apr. 18, 2016, 9 pages.
Notice of Allowance dated Jul. 19, 2018, issued in connection with U.S. Appl. No. 15/681,937, filed Aug. 21, 2017, 7 pages.
Notice of Allowance dated Mar. 20, 2018, issued in connection with U.S. Appl. No. 15/784,952, filed Oct. 16, 2017, 7 pages.
Notice of Allowance dated Aug. 22, 2017, issued in connection with U.S. Appl. No. 15/273,679, filed Sep. 22, 2016, 5 pages.
Notice of Allowance dated Jan. 22, 2018, issued in connection with U.S. Appl. No. 15/178,180, filed Jun. 9, 2016, 9 pages.
Notice of Allowance dated Dec. 29, 2017, issued in connection with U.S. Appl. No. 15/131,776, filed Apr. 18, 2016, 13 pages.
Notice of Allowance dated Mar. 9, 2018, issued in connection with U.S. Appl. No. 15/584,782, filed May 2, 2017, 8 pages.
Palm, Inc., “Handbook for the Palm VII Handheld,” May 2000, 311 pages.
Presentations at WinHEC 2000, May 2000, 138 pages.
Tsiami et al. “Experiments in acoustic source localization using sparse arrays in adverse indoors environments”, 2014 22nd European Signal Processing Conference, Sep. 1, 2014, 5 pages.
U.S. Appl. No. 60/490,768, filed Jul. 28, 2003, entitled “Method for synchronizing audio playback between multiple networked devices,” 13 pages.
U.S. Appl. No. 60/825,407, filed Sep. 12, 2006, entitled “Controlling and manipulating groupings in a multi-zone music or media system,” 82 pages.
UPnP; “Universal Plug and Play Device Architecture,” Jun. 8, 2000; version 1.0; Microsoft Corporation; pp. 1-54.
Vacher at al. “Recognition of voice commands by multisource ASR and noise cancellation in a smart home environment” Signal Processing Conference 2012 Proceedings of the 20th European, IEEE, Aug. 27, 2012, 5 pages.
Xiao et al. “A Learning-Based Approach to Direction of Arrival Estimation in Noisy and Reverberant Environments,” 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, Apr. 19, 2015, 5 pages.
Yamaha DME 64 Owner's Manual; copyright 2004, 80 pages.
Yamaha DME Designer 3.5 setup manual guide; copyright 2004, 16 pages.
Yamaha DME Designer 3.5 User Manual; Copyright 2004, 507 pages.
Non-Final Office Action dated Feb. 7, 2017, issued in connection with U.S. Appl. No. 15/131,244, filed Apr. 18, 2016, 12 pages.
Non-Final Office Action dated Feb. 8, 2017, issued in connection with U.S. Appl. No. 15/098,892, filed Apr. 14, 2016, 17 pages.
Non-Final Office Action dated Mar. 9, 2017, issued in connection with U.S. Appl. No. 15/098,760, filed Apr. 14, 2016, 13 pages.
Non-Final Office Action dated Jan. 10, 2018, issued in connection with U.S. Appl. No. 15/098,718, filed Apr. 14, 2016, 15 pages.
Non-Final Office Action dated Jan. 10, 2018, issued in connection with U.S. Appl. No. 15/229,868, filed Aug. 5, 2016, 13 pages.
Non-Final Office Action dated Jan. 10, 2018, issued in connection with U.S. Appl. No. 15/438,725, filed Feb. 21, 2017, 15 pages.
Non-Final Office Action dated Dec. 12, 2016, issued in connection with U.S. Appl. No. 15/098,718, filed Apr. 14, 2016, 11 pages.
Non-Final Office Action dated Jan. 13, 2017, issued in connection with U.S. Appl. No. 15/098,805, filed Apr. 14, 2016, 11 pages.
Non-Final Office Action dated Sep. 14, 2017, issued in connection with U.S. Appl. No. 15/178,180, filed Jun. 9, 2016, 16 pages.
Non-Final Office Action dated Mar. 16, 2018, issued in connection with U.S. Appl. No. 15/681,937, filed Aug. 21, 2017, 5 pages.
Non-Final Office Action dated Apr. 18, 2018, issued in connection with U.S. Appl. No. 15/811,468, filed Nov. 13, 2017, 14 pages.
Non-Final Office Action dated Apr. 19, 2017, issued in connection with U.S. Appl. No. 15/131,776, filed Apr. 18, 2016, 12 pages.
Non-Final Office Action dated Feb. 20, 2018, issued in connection with U.S. Appl. No. 15/211,748, filed Jul. 15, 2016, 31 pages.
Non-Final Office Action dated May 22, 2018, issued in connection with U.S. Appl. No. 15/946,599, filed Apr. 5, 2018, 19 pages.
Non-Final Office Action dated Jul. 25, 2017, issued in connection with U.S. Appl. No. 15/273,679, filed Jul. 22, 2016, 11 pages.
Non-Final Office Action dated Jan. 26, 2017, issued in connection with U.S. Appl. No. 15/098,867, filed Apr. 14, 2016, 16 pages.
Non-Final Office Action dated Oct. 26, 2017, issued in connection with U.S. Appl. No. 15/438,744, filed Feb. 21, 2017, 12 pages.
Advisory Action dated Jun. 28, 2018, issued in connection with U.S. Appl. No. 15/438,744, filed Feb. 21, 2017, 3 pages.
AudioTron Quick Start Guide, Version 1.0, Mar. 2001, 24 pages.
AudioTron Reference Manual, Version 3.0, May 2002, 70 pages.
AudioTron Setup Guide, Version 3.0, May 2002, 38 pages.
Bluetooth. “Specification of the Bluetooth System: The ad hoc SCATTERNET for affordable and highly functional wireless connectivity,” Core, Version 1.0 A, Jul. 26, 1999, 1068 pages.
Bluetooth. “Specification of the Bluetooth System: Wireless connections made easy,” Core, Version 1.0 B, Dec. 1, 1999, 1076 pages.
Corrected Notice of Allowability dated Mar. 8, 2017, issued in connection with U.S. Appl. No. 15/229,855, filed Aug. 5, 2016, 6 pages.
Dell, Inc. “Dell Digital Audio Receiver: Reference Guide,” Jun. 2000, 70 pages.
Dell, Inc. “Start Here,” Jun. 2000, 2 pages.
“Denon 2003-2004 Product Catalog,” Denon, 2003-2004, 44 pages.
European Patent Office, European Extended Search Report dated Oct. 30, 2017, issued in connection with EP Application No. 17174435.2, 11 pages.
Final Office Action dated Oct. 6, 2017, issued in connection with U.S. Appl. No. 15/098,760, filed Apr. 14, 2016, 25 pages.
Final Office Action dated Aug. 11, 2017, issued in connection with U.S. Appl. No. 15/131,776, filed Apr. 18, 2016, 7 pages.
Final Office Action dated Apr. 13, 2018, issued in connection with U.S. Appl. No. 15/131,254, filed Apr. 18, 2016, 18 pages.
Final Office Action dated Apr. 13, 2018, issued in connection with U.S. Appl. No. 15/438,744, filed Feb. 21, 2017, 20 pages.
Final Office Action dated Jun. 15, 2017, issued in connection with U.S. Appl. No. 15/098,718, filed Apr. 14, 2016, 15 pages.
Fiorenza Arisio et al. “Deliverable 1.1 User Study, analysis of requirements and definition of the application task,” May 31, 2012, http://dirha.fbk.eu/sites/dirha.fbk.eu/files/docs/DIRHA_D1.1., 31 pages.
Freiberger, Karl, “Development and Evaluation of Source Localization Algorithms for Coincident Microphone Arrays,” Diploma Thesis, Apr. 1, 2010, 106 pages.
International Searching Authority, International Search Report and Written Opinion dated Nov. 22, 2017, issued in connection with International Application No. PCT/US2017/054063, filed Sep. 28, 2017, 11 pages.
International Searching Authority, International Search Report and Written Opinion dated May 23, 2017, issued in connection with International Application No. PCT/US2017/018739, filed Feb. 21, 2017, 10 pages.
International Searching Authority, International Search Report and Written Opinion dated Oct. 23, 2017, issued in connection with International Application No. PCT/US2017/042170, filed Jul. 14, 2017, 15 pages.
International Searching Authority, International Search Report and Written Opinion dated Oct. 24, 2017, issued in connection with International Application No. PCT/US2017/042227, filed Jul. 14, 2017, 16 pages.
International Searching Authority, International Search Report and Written Opinion dated May 30, 2017, issued in connection with International Application No. PCT/US2017/018728, filed Feb. 21, 2017, 11 pages.
Jo et al., “Synchronized One-to-many Media Streaming with Adaptive Playout Control,” Proceedings of SPIE, 2002, pp. 71-82, vol. 4861.
Jones, Stephen, “Dell Digital Audio Receiver: Digital upgrade for your analog stereo,” Analog Stereo, Jun. 24, 2000 retrieved Jun. 18, 2014, 2 pages.
Louderback, Jim, “Affordable Audio Receiver Furnishes Homes With MP3,” TechTV Vault. Jun. 28, 2000 retrieved Jul. 10, 2014, 2 pages.
Morales-Cordovilla et al. “Room Localization for Distant Speech Recognition,” Proceedings of Interspeech 2014, Sep. 14, 2014, 4 pages.
Non-Final Office Action dated Jun. 1, 2017, issued in connection with U.S. Appl. No. 15/223,218, filed Jul. 29, 2016, 7 pages.
Non-Final Office Action dated Nov. 2, 2017, issued in connection with U.S. Appl. No. 15/584,782, filed May 2, 2017, 11 pages.
Non-Final Office Action dated Nov. 3, 2017, issued in connection with U.S. Appl. No. 15/438,741, filed Feb. 21, 2017, 11 pages.
Non-Final Office Action dated Jun. 27, 2018, issued in connection with U.S. Appl. No. 15/438,749, filed Feb. 21, 2017, 16 pages.
Non-Final Office Action dated Jun. 30, 2017, issued in connection with U.S. Appl. No. 15/277,810, filed Sep. 27, 2016, 13 pages.
Non-Final Office Action dated Feb. 6, 2018, issued in connection with U.S. Appl. No. 15/211,689, filed Jul. 15, 2016, 32 pages.
Non-Final Office Action dated Feb. 19, 2020, issued in connection with U.S. Appl. No. 16/148,879, filed Oct. 1, 2018, 15 pages.
Non-Final Office Action dated Jun. 20, 2019, issued in connection with U.S. Appl. No. 15/946,585, filed Apr. 5, 2018, 10 pages.
Non-Final Office Action dated Aug. 21, 2019, issued in connection with U.S. Appl. No. 16/192,126, filed Nov. 15, 2018, 8 pages.
Non-Final Office Action dated Feb. 21, 2019, issued in connection with U.S. Appl. No. 16/214,666, filed Dec. 10, 2018, 12 pages.
Non-Final Office Action dated Jan. 21, 2020, issued in connection with U.S. Appl. No. 16/214,711, filed Dec. 10, 2018, 9 pages.
Non-Final Office Action dated Jan. 21, 2020, issued in connection with U.S. Appl. No. 16/598,125, filed Oct. 10, 2019, 25 pages.
Non-Final Office Action dated Oct. 21, 2019, issued in connection with U.S. Appl. No. 15/973,413, filed May 7, 2018, 10 pages.
Non-Final Office Action dated May 23, 2019, issued in connection with U.S. Appl. No. 16/154,071, filed Oct. 8, 2018, 36 pages.
Non-Final Office Action dated Aug. 24, 2017, issued in connection with U.S. Appl. No. 15/297,627, filed Oct. 19, 2016, 13 pages.
Non-Final Office Action dated Jul. 24, 2019, issued in connection with U.S. Appl. No. 16/439,009, filed Jun. 12, 2019, 26 pages.
Non-Final Office Action dated Dec. 26, 2018, issued in connection with U.S. Appl. No. 16/154,469, filed Oct. 8, 2018, 7 pages.
Non-Final Office Action dated Jun. 27, 2019, issued in connection with U.S. Appl. No. 16/437,437, filed Jun. 11, 2019, 8 pages.
Non-Final Office Action dated Jun. 27, 2019, issued in connection with U.S. Appl. No. 16/437,476, filed Jun. 11, 2019, 8 pages.
Non-Final Office Action dated Mar. 27, 2020, issued in connection with U.S. Appl. No. 16/790,621, filed Feb. 13, 2020, 8 pages.
Non-Final Office Action dated May 27, 2020, issued in connection with U.S. Appl. No. 16/715,713, filed Dec. 16, 2019, 14 pages.
Non-Final Office Action dated Oct. 28, 2019, issued in connection with U.S. Appl. No. 16/145,275, filed Sep. 28, 2018, 11 pages.
Non-Final Office Action dated Mar. 29, 2019, issued in connection with U.S. Appl. No. 16/102,650, filed Aug. 13, 2018, 11 pages.
Non-Final Office Action dated Jul. 3, 2019, issued in connection with U.S. Appl. No. 15/948,541, filed Apr. 9, 2018, 7 pages.
Non-Final Office Action dated May 3, 2019, issued in connection with U.S. Appl. No. 16/178,122, filed Nov. 1, 2018, 14 pages.
Non-Final Office Action dated Oct. 3, 2018, issued in connection with U.S. Appl. No. 16/102,153, filed Aug. 13, 2018, 20 pages.
Non-Final Office Action dated Apr. 30, 2019, issued in connection with U.S. Appl. No. 15/718,521, filed Sep. 28, 2017, 39 pages.
Non-Final Office Action dated Apr. 4, 2019, issued in connection with U.S. Appl. No. 15/718,911, filed Sep. 28, 2017, 21 pages.
Non-Final Office Action dated Jan. 4, 2019, issued in connection with U.S. Appl. No. 15/948,541, filed Apr. 9, 2018, 6 pages.
Non-Final Office Action dated Apr. 6, 2020, issued in connection with U.S. Appl. No. 16/424,825, filed May 29, 2019, 22 pages.
Non-Final Office Action dated Mar. 6, 2020, issued in connection with U.S. Appl. No. 16/141,875, filed Sep. 25, 2018, 8 pages.
Non-Final Office Action dated Sep. 6, 2018, issued in connection with U.S. Appl. No. 15/098,760, filed Apr. 14, 2016, 29 pages.
Notice of Allowance dated Dec. 2, 2019, issued in connection with U.S. Appl. No. 15/718,521, filed Sep. 28, 2017, 15 pages.
Notice of Allowance dated Apr. 1, 2019, issued in connection with U.S. Appl. No. 15/935,966, filed Mar. 26, 2018, 5 pages.
Notice of Allowance dated Aug. 1, 2018, issued in connection with U.S. Appl. No. 15/297,627, filed Oct. 19, 2016, 9 pages.
Notice of Allowance dated Oct. 11, 2019, issued in connection with U.S. Appl. No. 16/437,476, filed Jun. 11, 2019, 9 pages.
Notice of Allowance dated Sep. 11, 2019, issued in connection with U.S. Appl. No. 16/154,071, filed Oct. 8, 2018, 5 pages.
Notice of Allowance dated Dec. 12, 2018, issued in connection with U.S. Appl. No. 15/811,468, filed Nov. 13, 2017, 9 pages.
Notice of Allowance dated Jun. 12, 2019, issued in connection with U.S. Appl. No. 15/670,361, filed Aug. 7, 2017, 7 pages.
Notice of Allowance dated Sep. 12, 2018, issued in connection with U.S. Appl. No. 15/438,744, filed Feb. 21, 2017, 15 pages.
Notice of Allowance dated Feb. 13, 2019, issued in connection with U.S. Appl. No. 15/959,907, filed Apr. 23, 2018, 10 pages.
Notice of Allowance dated Jan. 13, 2020, issued in connection with U.S. Appl. No. 16/192,126, filed Nov. 15, 2018, 6 pages.
Notice of Allowance dated Nov. 14, 2018, issued in connection with U.S. Appl. No. 15/297,627, filed Oct. 19, 2016, 5 pages.
Notice of Allowance dated Jan. 15, 2020, issued in connection with U.S. Appl. No. 16/439,009, filed Jun. 12, 2019, 9 pages.
Notice of Allowance dated Mar. 15, 2019, issued in connection with U.S. Appl. No. 15/804,776, filed Nov. 6, 2017, 9 pages.
Notice of Allowance dated Oct. 15, 2019, issued in connection with U.S. Appl. No. 16/437,437, filed Jun. 11, 2019, 9 pages.
Notice of Allowance dated Jul. 17, 2019, issued in connection with U.S. Appl. No. 15/718,911, filed Sep. 28, 2017, 5 pages.
Notice of Allowance dated Sep. 17, 2018, issued in connection with U.S. Appl. No. 15/211,689, filed Jul. 15, 2016, 6 pages.
Notice of Allowance dated Apr. 18, 2019, issued in connection with U.S. Appl. No. 16/173,797, filed Oct. 29, 2018, 9 pages.
Notice of Allowance dated Dec. 18, 2019, issued in connection with U.S. Appl. No. 16/434,426, filed Jun. 7, 2019, 13 pages.
Notice of Allowance dated Feb. 18, 2020, issued in connection with U.S. Appl. No. 16/022,662, filed Jun. 28, 2018, 8 pages.
Notice of Allowance dated Jul. 18, 2019, issued in connection with U.S. Appl. No. 15/438,749, filed Feb. 21, 2017, 9 pages.
Notice of Allowance dated Jul. 18, 2019, issued in connection with U.S. Appl. No. 15/721,141, filed Sep. 29, 2017, 8 pages.
Notice of Allowance dated Dec. 19, 2018, issued in connection with U.S. Appl. No. 15/818,051, filed Nov. 20, 2017, 9 pages.
Notice of Allowance dated Aug. 2, 2019, issued in connection with U.S. Appl. No. 16/102,650, filed Aug. 13, 2018, 5 pages.
Notice of Allowance dated Sep. 20, 2018, issued in connection with U.S. Appl. No. 15/946,599, filed Apr. 5, 2018, 7 pages.
Hirano et al. “A Noise-Robust Stochastic Gradient Algorithm with an Adaptive Step-Size Suitable for Mobile Hands-Free Telephones,” 1995, International Conference on Acoustics, Speech, and Signal Processing, vol. 2, 4 pages.
International Bureau, International Preliminary Report on Patentability, dated Apr. 11, 2019, issued in connection with International Application No. PCT/US2017/0054063, filed on Sep. 28, 2017, 9 pages.
International Bureau, International Preliminary Report on Patentability, dated Feb. 20, 2020, issued in connection with International Application No. PCT/US2018/045397, filed on Aug. 6, 2018, 8 pages.
International Bureau, International Preliminary Report on Patentability, dated Apr. 23, 2019, issued in connection with International Application No. PCT/US2017/057220, filed on Oct. 18, 2017, 7 pages.
International Bureau, International Preliminary Report on Patentability, dated Mar. 31, 2020, issued in connection with International Application No. PCT/US2018053123, filed on Sep. 27, 2018, 12 pages.
International Bureau, International Preliminary Report on Patentability, dated Mar. 31, 2020, issued in connection with International Application No. PCT/US2018053472, filed on Sep. 28, 2018, 8 pages.
International Bureau, International Preliminary Report on Patentability, dated Mar. 31, 2020, issued in connection with International Application No. PCT/US2018053517, filed on Sep. 28, 2018, 10 pages.
International Bureau, International Preliminary Report on Patentability, dated Sep. 7, 2018, issued in connection with International Application No. PCT/US2017/018728, filed on Feb. 21, 2017, 8 pages.
International Bureau, International Preliminary Report on Patentability, dated Sep. 7, 2018, issued in connection with International Application No. PCT/US2017/018739, filed on Feb. 21, 2017, 7 pages.
International Bureau, International Search Report and Written Opinion dated Nov. 18, 2019, issued in connection with International Application No. PCT/US2019052841, filed on Sep. 25, 2019, 12 pages.
International Bureau, International Search Report and Written Opinion dated Mar. 2, 2020, issued in connection with International Application No. PCT/US2019064907, filed on Dec. 6, 2019, 11 pages.
International Bureau, International Search Report and Written Opinion dated Dec. 20, 2019, issued in connection with International Application No. PCT/US2019052654, filed on Sep. 24, 2019, 11 pages.
International Bureau, International Search Report and Written Opinion dated Dec. 6, 2019, issued in connection with International Application No. PCT/US2019050852, filed on Sep. 12, 2019, 10 pages.
International Bureau, International Search Report and Written Opinion dated Apr. 8, 2020, issued in connection with International Application No. PCT/US2019/067576, filed on Dec. 19, 2019, 12 pages.
International Searching Authority, International Search Report and Written Opinion dated Dec. 19, 2018, in connection with International Application No. PCT/US2018/053517, 13 pages.
International Searching Authority, International Search Report and Written Opinion dated Jan. 23, 2018, issued in connection with International Application No. PCT/US2017/57220, filed on Oct. 18, 2017, 8 pages.
Japanese Patent Office, Non-Final Office Action and Translation dated Nov. 5, 2019, issued in connection with Japanese Patent Application No. 2019-517281, 6 pages.
Japanese Patent Office, Office Action and Translation dated Oct. 8, 2019, issued in connection with Japanese Patent Application No. 2019-521032, 5 pages.
Japanese Patent Office, Office Action Translation dated Nov. 5, 2019, issued in connection with Japanese Patent Application No. 2019-517281, 2 pages.
Japanese Patent Office, Office Action Translation dated Oct. 8, 2019, issued in connection with Japanese Patent Application No. 2019-521032, 8 pages.
Jose Alvarez and Mathieu Salzmann “Compression-aware Training of Deep Networks” 31st Conference on Neural Information Processing Systems, Nov. 13, 2017, 12pages.
Korean Patent Office, Korean Office Action and Translation dated Aug. 16, 2019, issued in connection with Korean Application No. 10-2018-7027452, 14 pages.
Korean Patent Office, Korean Office Action and Translation dated Apr. 2, 2020, issued in connection with Korean Application No. 10-2020-7008486, 12 pages.
Korean Patent Office, Korean Office Action and Translation dated Mar. 25, 2020, issued in connection with Korean Application No. 10-2019-7012192, 14 pages.
Korean Patent Office, Korean Office Action and Translation dated Mar. 30, 2020, issued in connection with Korean Application No. 10-2020-7004425, 5 pages.
Korean Patent Office, Korean Office Action and Translation dated Sep. 9, 2019, issued in connection with Korean Application No. 10-2018-7027451, 21 pages.
Korean Patent Office, Korean Office Action dated May 8, 2019, issued in connection with Korean Application No. 10-2018-7027451, 7 pages.
Korean Patent Office, Korean Office Action dated May 8, 2019, issued in connection with Korean Application No. 10-2018-7027452, 5 pages.
Maja Taseska and Emanual A.P. Habets, “MMSE-Based Blind Source Extraction in Diffuse Noise Fields Using a Complex Coherence-Based a Priori Sap Estimator” International Workshop on Acoustic Signal Enhancement 2012, Sep. 4-6, 2012, 4pages.
Newman, Jared. “Chromecast Audio's multi-room support has arrived,” Dec. 11, 2015, https://www.pcworld.com/article/3014204/customer-electronic/chromcase-audio-s-multi-room-support-has . . . , 1 page.
Ngo et al. “Incorporating the Conditional Speech Presence Probability in Multi-Channel Wiener Filter Based Noise Reduction in Hearing Aids.” EURASIP Journal on Advances in Signal Processing vol. 2009, Jun. 2, 2009, 11 pages.
Non-Final Office Action dated Nov. 4, 2019, issued in connection with U.S. Appl. No. 16/022,662, filed Jun. 28, 2018, 16 pages.
Non-Final Office Action dated Sep. 5, 2019, issued in connection with U.S. Appl. No. 16/416,752, filed May 20, 2019, 14 pages.
Non-Final Office Action dated Oct. 9, 2019, issued in connection with U.S. Appl. No. 15/936,177, filed Mar. 26, 2018, 16 pages.
Non-Final Office Action dated Sep. 10, 2018, issued in connection with U.S. Appl. No. 15/670,361, filed Aug. 7, 2017, 17 pages.
Non-Final Office Action dated Oct. 11, 2019, issued in connection with U.S. Appl. No. 16/177,185, filed Oct. 31, 2018, 14 pages.
Non-Final Office Action dated Feb. 12, 2019, issued in connection with U.S. Appl. No. 15/670,361, filed Aug. 7, 2017, 13 pages.
Non-Final Office Action dated Nov. 13, 2018, issued in connection with U.S. Appl. No. 15/717,621, filed Sep. 27, 2017, 23 pages.
Non-Final Office Action dated Nov. 13, 2018, issued in connection with U.S. Appl. No. 16/160,107, filed Oct. 15, 2018, 8 pages.
Non-Final Office Action dated May 14, 2020, issued in connection with U.S. Appl. No. 15/948,541, filed Apr. 9, 2018, 8 pages.
Non-Final Office Action dated Sep. 14, 2018, issued in connection with U.S. Appl. No. 15/959,907, filed Apr. 23, 2018, 15 pages.
Non-Final Office Action dated Apr. 15, 2020, issued in connection with U.S. Appl. No. 16/138,111, filed Sep. 21, 2018, 15 pages.
Non-Final Office Action dated Jan. 15, 2019, issued in connection with U.S. Appl. No. 16/173,797, filed Oct. 29, 2018, 6 pages.
Non-Final Office Action dated Nov. 15, 2019, issued in connection with U.S. Appl. No. 16/153,530, filed Oct. 5, 2018, 17 pages.
Non-Final Office Action dated Oct. 16, 2018, issued in connection with U.S. Appl. No. 15/131,254, filed Apr. 18, 2016, 16 pages.
Non-Final Office Action dated Jan. 18, 2019, issued in connection with U.S. Appl. No. 15/721,141, filed Sep. 29, 2017, 18 pages.
Non-Final Office Action dated Oct. 18, 2019, issued in connection with U.S. Appl. No. 15/098,760, filed Apr. 14, 2016, 27 pages.
Non-Final Office Action dated Sep. 18, 2019, issued in connection with U.S. Appl. No. 16/179,779, filed Nov. 2, 2018, 14 pages.
Non-Final Office Action dated Dec. 19, 2019, issued in connection with U.S. Appl. No. 16/147,710, filed Sep. 29, 2018, 10 pages.
Advisory Action dated Apr. 24, 2020, issued in connection with U.S. Appl. No. 15/948,541, filed Apr. 9, 2018, 4 pages.
Advisory Action dated Dec. 31, 2018, issued in connection with U.S. Appl. No. 15/804,776, filed Nov. 6, 2017, 4 pages.
Anonymous,. S Voice or Google Now—The Lowdown. Apr. 28, 2015, 9 pages. [online], [retrieved on Nov. 29, 2017]. Retrieved from the Internet (URL:http://web.archive.org/web/20160807040123/http://lowdown.carphonewarehouse.com/news/s-voice-or-google-now/29958/).
Australian Patent Office, Australian Examination Report Action dated Apr. 14, 2020, issued in connection with Australian Application No. 2019202257, 3 pages.
Australian Patent Office, Australian Examination Report Action dated Oct. 3, 2019, issued in connection with Australian Application No. 2018230932, 3 pages.
Australian Patent Office, Examination Report dated Oct. 30, 2018, issued in connection with Australian Application No. 2017222436, 3 pages.
“Automatic Parameter Tying in Neural Networks” ICLR 2018, 14 pages.
Canadian Patent Office, Canadian Office Action dated Nov. 14, 2018, issued in connection with Canadian Application No. 3015491, 3 pages.
Chinese Patent Office, First Office Action and Translation dated Mar. 20, 2019, issued in connection with Chinese Application No. 201780025028.2, 18 pages.
Chinese Patent Office, First Office Action and Translation dated Mar. 27, 2019, issued in connection with Chinese Application No. 201780025029.7, 9 pages.
Chinese Patent Office, First Office Action and Translation dated Nov. 5, 2019, issued in connection with Chinese Application No. 201780072651.3, 19 pages.
Chinese Patent Office, First Office Action dated Feb. 20, 2020, issued in connection with Chinese Application No. 201780061543.6, 29 pages.
Chinese Patent Office, Second Office Action and Translation dated May 11, 2020, issued in connection with Chinese Application No. 201780061543.6, 17 pages.
Chinese Patent Office, Second Office Action and Translation dated Jul. 18, 2019, issued in connection with Chinese Application No. 201780025029.7, 14 pages.
Chinese Patent Office, Second Office Action and Translation dated Sep. 23, 2019, issued in connection with Chinese Application No. 201780025028.2, 15 pages.
Chinese Patent Office, Second Office Action and Translation dated Mar. 31, 2020, issued in connection with Chinese Application No. 201780072651.3, 17 pages.
Chinese Patent Office, Third Office Action and Translation dated Sep. 16, 2019, issued in connection with Chinese Application No. 201780025029.7, 14 pages.
Chinese Patent Office, Translation of Office Action dated Jul. 18, 2019, issued in connection with Chinese Application No. 201780025029.7, 8 pages.
Cipriani,. The complete list of OK, Google commands—CNET. Jul. 1, 2016, 5 pages. [online], [retrieved on Jan. 15, 2020]. Retrieved from the Internet: (URL:https://web.archive.org/web/20160803230926/https://www.cnet.com/how-to/complete-list-of-ok-google--commands/).
European Patent Office, European Extended Search Report dated Feb. 3, 2020, issued in connection with European Application No. 19197116.7, 9 pages.
European Patent Office, European Extended Search Report dated Jan. 3, 2019, issued in connection with European Application No. 177570702, 8 pages.
European Patent Office, European Extended Search Report dated Jan. 3, 2019, issued in connection with European Application No. 17757075.1, 9 pages.
European Patent Office, European Office Action dated Jan. 14, 2020, issued in connection with European Application No. 177570702, 7 pages.
European Patent Office, European Office Action dated Jan. 22, 2019, issued in connection with European Application No. 171744352, 9 pages.
European Patent Office, European Office Action dated Aug. 30, 2019, issued in connection with European Application No. 17781608.9, 6 pages.
European Patent Office, Summons to Attend Oral Proceedings mailed on Dec. 20, 2019, issued in connection with European Application No. 17174435.2, 13 pages.
Fadilpasic,“Cortana can now be the default PDA on your Android”, IT Pro Portal: Accessed via WayBack Machine; http://web.archive.org/web/20171129124915/https://www.itproportal.com/2015/08/11/cortana-can-now-be- . . . , Aug. 11, 2015, 6 pages.
Final Office Action dated Apr. 11, 2019, issued in connection with U.S. Appl. No. 15/131,254, filed Apr. 18, 2016, 17 pages.
Final Office Action dated Dec. 11, 2019, issued in connection with U.S. Appl. No. 16/227,308, filed Dec. 20, 2018, 10 pages.
Final Office Action dated Sep. 11, 2019, issued in connection with U.S. Appl. No. 16/178,122, filed Nov. 1, 2018, 13 pages.
Final Office Action dated May 13, 2020, issued in connection with U.S. Appl. No. 16/153,530, filed Oct. 5, 2018, 20 pages.
Final Office Action dated Oct. 15, 2018, issued in connection with U.S. Appl. No. 15/804,776, filed Nov. 6, 2017, 18 pages.
Final Office Action dated Oct. 16, 2018, issued in connection with U.S. Appl. No. 15/438,725, filed Feb. 21, 2017, 10 pages.
Final Office Action dated May 18, 2020, issued in connection with U.S. Appl. No. 16/177,185, filed Oct. 31, 2018, 16 pages.
Final Office Action dated Feb. 21, 2018, issued in connection with U.S. Appl. No. 15/297,627, filed Oct. 19, 2016, 12 pages.
Final Office Action May 21, 2020, issued in connection with U.S. Appl. No. 15/989,715, filed May 25, 2018, 21 pages.
Final Office Action dated Mar. 23, 2020, issued in connection with U.S. Appl. No. 16/145,275, filed Sep. 28, 2018, 11 pages.
Final Office Action dated Feb. 24, 2020, issued in connection with U.S. Appl. No. 15/936,177, filed Mar. 26, 2018, 20 pages.
Final Office Action dated Apr. 26, 2019, issued in connection with U.S. Appl. No. 15/721,141, filed Sep. 29, 2017, 20 pages.
Final Office Action dated Apr. 30, 2019, issued in connection with U.S. Appl. No. 15/098,760, filed Apr. 14, 2016, 6 pages.
Final Office Action dated Feb. 5, 2019, issued in connection with U.S. Appl. No. 15/438,749, filed Feb. 21, 2017, 17 pages.
Final Office Action dated Feb. 7, 2020, issued in connection with U.S. Appl. No. 15/948,541, filed Apr. 9, 2018, 8 pages.
First Action Interview Office Action dated Aug. 14, 2019, issued in connection with U.S. Appl. No. 16/227,308, filed Dec. 20, 2018, 4 pages.
First Action Interview Office Action dated Jun. 2, 2020, issued in connection with U.S. Appl. No. 16/109,375, filed Aug. 22, 2018, 10 pages.
First Action Interview Office Action dated Jan. 22, 2020, issued in connection with U.S. Appl. No. 15/989,715, filed May 25, 2018, 3 pages.
First Action Interview Office Action dated Jul. 5, 2019, issued in connection with U.S. Appl. No. 16/227,308, filed Dec. 20, 2018, 4 pages.
Giacobello et al. “A Sparse Nonuniformly Partitioned Multidelay Filter for Acoustic Echo Cancellation,” 2013, IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct. 2013, New Paltz, NY, 4 pages.
Giacobello et al. “Tuning Methodology for Speech Enhancement Algorithms using a Simulated Conversational Database and Perceptual Objective Measures,” 2014, 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays HSCMA, 2014, 5 pages.
Han et al. “Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.” ICLR 2016, Feb. 15, 2016, 14 pages.
Helwani et al “Source-domain adaptive filtering for MIMO systems with application to acoustic echo cancellation”, Acoustics Speech and Signal Processing, 2010 IEEE International Conference, Mar. 14, 2010, 4 pages.
Notice of Allowance dated Feb. 21, 2020, issued in connection with U.S. Appl. No. 16/416,752, filed May 20, 2019, 6 pages.
Notice of Allowance dated Jan. 21, 2020, issued in connection with U.S. Appl. No. 16/672,764, filed Nov. 4, 2019, 10 pages.
Notice of Allowance dated Oct. 21, 2019, issued in connection with U.S. Appl. No. 15/946,585, filed Apr. 5, 2018, 5 pages.
Notice of Allowance dated Apr. 24, 2019, issued in connection with U.S. Appl. No. 16/154,469, filed Oct. 8, 2018, 5 pages.
Notice of Allowance dated Apr. 27, 2020, issued in connection with U.S. Appl. No. 16/700,607, filed Dec. 2, 2019, 10 pages.
Notice of Allowance dated Mar. 27, 2019, issued in connection with U.S. Appl. No. 16/214,666, filed Dec. 10, 2018, 6 pages.
Notice of Allowance dated Mar. 28, 2018, issued in connection with U.S. Appl. No. 15/699,982, filed Sep. 8, 2017, 17 pages.
Notice of Allowance dated May 29, 2020, issued in connection with U.S. Appl. No. 16/148,879, filed Oct. 1, 2018, 6 pages.
Notice of Allowance dated Apr. 3, 2019, issued in connection with U.S. Appl. No. 16/160,107, filed Oct. 15, 2018, 7 pages.
Notice of Allowance dated Jul. 30, 2018, issued in connection with U.S. Appl. No. 15/098,718, filed Apr. 14, 2016, 5 pages.
Notice of Allowance dated Jul. 30, 2019, issued in connection with U.S. Appl. No. 15/131,254, filed Apr. 18, 2016, 9 pages.
Notice of Allowance dated Mar. 30, 2020, issued in connection with U.S. Appl. No. 15/973,413, filed May 7, 2018, 5 pages.
Notice of Allowance dated Nov. 30, 2018, issued in connection with U.S. Appl. No. 15/438,725, filed Feb. 21, 2017, 5 pages.
Notice of Allowance dated Oct. 30, 2019, issued in connection with U.S. Appl. No. 16/131,392, filed Sep. 14, 2018, 9 pages.
Notice of Allowance dated May 31, 2019, issued in connection with U.S. Appl. No. 15/717,621, filed Sep. 27, 2017, 9 pages.
Notice of Allowance dated Mar. 4, 2020, issued in connection with U.S. Appl. No. 16/444,975, filed Jun. 18, 2019, 10 pages.
Notice of Allowance dated Feb. 5, 2020, issued in connection with U.S. Appl. No. 16/178,122, filed Nov. 1, 2018, 9 pages.
Notice of Allowance dated Oct. 5, 2018, issued in connection with U.S. Appl. No. 15/211,748, filed Jul. 15, 2018, 10 pages.
Notice of Allowance dated Feb. 6, 2019, issued in connection with U.S. Appl. No. 16/102,153, filed Aug. 13, 2018, 9 pages.
Notice of Allowance dated Feb. 6, 2020, issued in connection with U.S. Appl. No. 16/227,308, filed Dec. 20, 2018, 7 pages.
Notice of Allowance dated Apr. 7, 2020, issued in connection with U.S. Appl. No. 15/098,760, filed Apr. 14, 2016, 7 pages.
Notice of Allowance dated Apr. 7, 2020, issued in connection with U.S. Appl. No. 16/147,710, filed Sep. 29, 2018, 15 pages.
Notice of Allowance dated Jun. 7, 2019, issued in connection with U.S. Appl. No. 16/102,153, filed Aug. 13, 2018, 9 pages.
Notice of Allowance dated Aug. 9, 2018, issued in connection with U.S. Appl. No. 15/229,868, filed Aug. 5, 2016, 11 pages.
Optimizing Siri on HomePod in Far-Field Settings. Audio Software Engineering and Siri Speech Team, Machine Learning Journal vol. 1, Issue 12. https://machinelearning.apple.com/2018/12/03/optimizing-siri-on-homepod-in-far-field-settings.html. Dec. 2018, 18 pages.
Preinterview First Office Action dated Aug. 5, 2019, issued in connection with U.S. Appl. No. 16/434,426, filed Jun. 7, 2019, 4 pages.
Preinterview First Office Action dated Mar. 25, 2020, issued in connection with U.S. Appl. No. 16/109,375, filed Aug. 22, 2018, 6 pages.
Preinterview First Office Action dated Sep. 30, 2019, issued in connection with U.S. Appl. No. 15/989,715, filed May 25, 2018, 4 pages.
Preinterview First Office Action dated May 7, 2020, issued in connection with U.S. Appl. No. 16/213,570, filed Dec. 7, 2018, 5 pages.
Restriction Requirement dated Aug. 14, 2019, issued in connection with U.S. Appl. No. 16/214,711, filed Dec. 10, 2018, 5 pages.
Restriction Requirement dated Aug. 9, 2018, issued in connection with U.S. Appl. No. 15/717,621, filed Sep. 27, 2017, 8 pages.
Souden et al. “An Integrated Solution for Online Multichannel Noise Tracking and Reduction.” IEEE Transactions on Audio, Speech, and Language Processing, vol. 19. No. 7, Sep. 7, 2011, 11 pages.
Souden et al. “Gaussian Model-Based Multichannel Speech Presence Probability” IEEE Transactions on Audio, Speech, and Language Processing, vol. 18, No. 5, Jul. 5, 2010, 6pages.
Souden et al. “On Optimal Frequency-Domain Multichannel Linear Filtering for Noise Reduction.” IEEE Transactions on Audio, Speech, and Language Processing, vol. 18, No. 2, Feb. 2010, 17pages.
Steven J. Nowlan and Geoffrey E. Hinton “Simplifying Neural Networks by Soft Weight-Sharing” Neural Computation 4, 1992, 21 pages.
Tweet “How to start using Google app voice commands to make your life easier Share This Story shop @Bullet”, Jan. 21, 2016, https://bgr.com/2016/01/21/best-ok-google-voice-commands/, 3 page.
Ullrich et al. “Soft Weight-Sharing for Neural Network Compression.” ICLR 2017, 16 pages.
Vacher et al. “Speech Recognition in a Smart Home: Some Experiments for Telemonitoring,” 2009 Proceedings of the 5th Conference on Speech Technology and Human-Computer Dialogoue, Constant, 2009, 10 pages.
“S Voice or Google Now?”; https://web.archive.org/web/20160807040123/lowdown.carphonewarehouse.com/news/s-voice-or-google-now/ . . . , Apr. 28, 2015; 4 pages.
Wung et al. “Robust Acoustic Echo Cancellation in the Short-Time Fourier Transform Domain Using Adaptive Crossband Filters” IEEE International Conference on Acoustic, Speech and Signal Processing ICASSP, 2014, p. 1300-1304.
Yamaha DME Designer 3.0 Owner's Manual; Copyright 2008, 501 pages.

Related Publications (1)

	Number	Date	Country
	20190355384 A1	Nov 2019	US

Linear filtering for noise-suppressed speech detection

Information

Patent Number

Date Filed

Date Issued

Inventors

Original Assignees

Examiners

Agents

CPC

Field of Search

US

CPC