Patent Grant
8862471
1. Field of the Invention
The field of the invention is data processing, or, more specifically, methods, apparatus, and products for establishing a multimodal advertising personality for a sponsor of a multimodal application.
2. Description of Related Art
User interaction with applications running on small devices through a keyboard or stylus has become increasingly limited and cumbersome as those devices have become increasingly smaller. In particular, small handheld devices like mobile phones and PDAs serve many functions and contain sufficient processing power to support user interaction through other modes, such as multimodal access. Devices which support multimodal access combine multiple user input modes or channels in the same interaction allowing a user to interact with the applications on the device simultaneously through multiple input modes or channels. The methods of input include speech recognition, keyboard, touch screen, stylus, mouse, handwriting, and others. Multimodal input often makes using a small device easier.
Multimodal applications often run on servers that serve up multimodal web pages for display on a multimodal browser. A ‘multimodal browser,’ as the term is used in this specification, generally means a web browser capable of receiving multimodal input and interacting with users with multimodal output. Multimodal browsers typically render web pages written in XHTML+Voice (‘X+V’). X+V provides a markup language that enables users to interact with an multimodal application often running on a server through spoken dialog in addition to traditional means of input such as keyboard strokes and mouse pointer action. Visual markup tells a multimodal browser what the user interface is look like and how it is to behave when the user types, points, or clicks. Similarly, voice markup tells a multimodal browser what to do when the user speaks to it. For visual markup, the multimodal browser uses a graphics engine; for voice markup, the multimodal browser uses a speech engine. X+V adds spoken interaction to standard web content by integrating XHTML (eXtensible Hypertext Markup Language) and speech recognition vocabularies supported by VoiceXML. For visual markup, X+V includes the XHTML standard. For voice markup, X+V includes a subset of VoiceXML. For synchronizing the VoiceXML elements with corresponding visual interface elements, X+V uses events. XHTML includes voice modules that support speech synthesis, speech dialogs, command and control, and speech grammars. Voice handlers can be attached to XHTML elements and respond to specific events. Voice interaction features are integrated with XHTML and can consequently be used directly within XHTML content.
In addition to X+V, multimodal applications also may be implemented with Speech Application Tags (‘SALT’). SALT is a markup language developed by the Salt Forum. Both X+V and SALT are markup languages for creating applications that use voice input/speech recognition and voice output/speech synthesis. Both SALT applications and X+V applications use underlying speech recognition and synthesis technologies or ‘speech engines’ to do the work of recognizing and generating human speech. As markup languages, both X+V and SALT provide markup-based programming environments for using speech engines in an application's user interface. Both languages have language elements, markup tags, that specify what the speech-recognition engine should listen for and what the synthesis engine should ‘say.’ Whereas X+V combines XHTML, VoiceXML, and the XML Events standard to create multimodal applications, SALT does not provide a standard visual markup language or eventing Model. Rather, it is a low-level set of tags for specifying voice interaction that can be embedded into other environments. In addition to X+V and SALT, multimodal applications may be implemented in Java with a Java speech framework, in C++, for example, and with other technologies and in other environments as well.
Current lightweight voice solutions require a developer to build a grammar and lexicon to limit the potential number of words that an automated speech recognition (‘ASR’) engine must recognize—as a means for increasing accuracy. Pervasive devices have limited interaction and input modalities due to the form factor of the device, and kiosk devices have limited interaction and input modalities by design. In both cases the use of speaker independent voice recognition is implemented to enhance the user experience and interaction with the device. The state of the art in speaker independent recognition allows for some sophisticated voice applications to be written as long as there is a limited vocabulary associated with each potential voice command. For example, if the user is prompted to speak the name of a city the system can, with a decent level of confidence, recognize the name of the city spoken. In the case where there is no explicit context, such as a blank text field for inputting any search query, this speaker independent recognition fails because a reasonably sized vocabulary is not available.
Incorporating speech into web applications enables new methods for advertising sponsors to reach and sell to customers. The modes in which advertising is delivered are often directly associated with a customer's perception of a sponsoring company. The application developer is now faced with the responsibility of presenting the sponsor's web application through modes that are acceptable to the company and attractive to end users.
Methods, apparatus, and computer program products are described for establishing a multimodal advertising personality for a sponsor of a multimodal application that include associating one or more vocal demeanors with a sponsor of a multimodal application and presenting a speech portion of the multimodal application for the sponsor using at least one of the vocal demeanors associated with the sponsor.
The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular descriptions of exemplary embodiments of the invention as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts of exemplary embodiments of the invention.
Exemplary methods, apparatus, and products for establishing a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention are described with reference to the accompanying drawings, beginning with
A multimodal device is an automated device, that is, automated computing machinery or a computer program running on an automated device, that is capable of accepting from users more than one mode of input, keyboard, mouse, stylus, and so on, including speech input—and also displaying more than one mode of output, graphic, speech, and so on. A multimodal device is generally capable of accepting speech input from a user, digitizing the speech, and providing digitized speech to a speech engine for recognition. A multimodal device may be implemented, for example, as a voice-enabled browser on a laptop, a voice browser on a telephone handset, an online game implemented with Java on a personal computer, and with other combinations of hardware and software as may occur to those of skill in the art. Because multimodal applications may be implemented in markup languages (X+V, SALT), object-oriented languages (Java, C++), procedural languages (the C programming language), and in other kinds of computer languages as may occur to those of skill in the art, this specification uses the term ‘multimodal application’ to refer to any software application, server-oriented or client-oriented, thin client or thick client, that administers more than one mode of input and more than one mode of output, typically including visual and speech modes.
The system of
Each of the example multimodal devices (152) in the system of
As mentioned, a multimodal device according to embodiments of the present invention, is capable of providing speech to a speech engine for recognition. A speech engine is a functional module, typically a software module, although it may include specialized hardware also, that does the work of recognizing and generating or ‘synthesizing’ human speech. The speech engine implements speech recognition by use of a further module referred to in this specification as a ASR engine, and the speech engine carries out speech synthesis by use of a further module referred to in this specification as a text-to-speech (‘TTS’) engine. As shown in
Each of the example multimodal devices (152) in the system of
The use of these four example multimodal devices (152) is for explanation only, not for limitation of the invention. Any automated computing machinery capable of accepting speech from a user, providing the speech digitized to an ASR engine, and receiving and playing speech prompts and responses from the voice server may be improved to function as a multimodal device for establishing a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention.
The system of
The system of
The system of
The arrangement of the voice server (151), the multimodal devices (152), and the data communications network (100) making up the exemplary system illustrated in
Establishing a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention in a thin client architecture typically is implemented with one or more voice servers, computers, that is, automated computing machinery, that provide speech recognition and speech synthesis. For further explanation, therefore,
Stored in RAM (168) is a multimodal server application (188), a module of computer program instructions capable of operating a voice server in a system that is configured to establish a multimodal advertising personality for a multimodal application according to embodiments of the present invention. Multimodal server application (188) provides voice recognition services for multimodal devices by accepting requests for speech recognition and returning speech recognition results, including text representing recognized speech, text for use as variable values in dialogs, and text as string representations of scripts for semantic interpretation. Multimodal server application (188) also includes computer program instructions that provide text-to-speech (‘TTS’) conversion for voice prompts and voice responses to user input in multimodal applications such as, for example, X+V applications, SALT applications, or Java Speech applications.
Multimodal server application (188) in this example is also configured to establish a multimodal advertising personality for a multimodal application according to embodiments of the present invention by associating one or more vocal demeanors (550) with a sponsor (503) of a multimodal application and presenting a speech portion of the multimodal application for the sponsor using at least one of the vocal demeanors associated with the sponsor. In this example, both vocal demeanors (550) and sponsors (503) are represented as values of data structures stored in RAM (168). According to embodiments of the present invention, a sponsor may purchase from an owner of the multimodal application exclusive use of a vocal demeanor within the multimodal application. Alternatively, a sponsor may purchase from an owner of the multimodal application exclusive use of a set of vocal demeanors within the multimodal application, including a right to exclude from use within a portion of the multimodal application all vocal demeanors not in the set of vocal demeanors. The multimodal application may select, among the set of vocal demeanors, a vocal demeanor for presentation of a speech portion of the multimodal application for the sponsor in dependence upon sponsor-provided rules. In addition to such use of a vocal demeanor, establishing a multimodal advertising personality according to embodiments of the present invention may also include purchasing by a sponsor from an owner of the multimodal application exclusive use of one or more visual demeanors within the multimodal application; associating one or more visual demeanors with the sponsor of a multimodal application; and presenting a visual portion of the multimodal application for the sponsor using at least one of the visual demeanors associated with the sponsor.
The multimodal application in this example may be viewed as a combination of the multimodal server application and a remote multimodal device application cooperating through a VOIP protocol to establish a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention. The multimodal device application, located on a multimodal device across a network from the voice server, is the so-called ‘thin client,’ so-called because much of the functionality for establishing the multimodal advertising personality is implemented on the voice server rather than on the multimodal device. The multimodal server application (188) can incorporate a selected vocal demeanor (550) as a component of a multimodal advertising personality into the multimodal server application by linking one or more markup elements of a markup document of the multimodal server application to one or more styles of a Cascading Style Sheet (‘CSS’) (514) and providing the CSS to a requesting multimodal device application that in turn loads the CSS into a multimodal device application and uses the CSS to control a multimodal user interface, that is, the voice aspects of a multimodal user interface.
Cascading Style Sheets is a stylesheet language used to describe the presentation of a document written in a markup language. The common application of CSS is to style web pages written in HTML and XHTML, but the language can be applied to any kind of XML document, including Scalable Vector Graphics (“SVG”) and XML User Interface Language (“XUL”). The CSS specifications are maintained by the World Wide Web Consortium (“W3C”). CSS can control the vocal display of an X+V page as well as the visual display. The aural rendering of a document, already commonly used by the blind and print-impaired communities, combines speech synthesis and “auditory icons.” Often such aural presentation occurs by converting the document to plain text and feeding this to a screen reader—software or hardware that simply reads all the characters on the screen. This results in less effective presentation than would be the case if the document structure were retained. Style sheet properties for aural presentation may be used together with visual properties (mixed media or multimodal) or as, an aural alternative to visual presentation. When using aural properties, the aural CSS canvas consists of a three-dimensional physical space (sound surrounds) and a temporal space (one may specify sounds before, during, and after other sounds). The CSS properties also allow authors to vary the quality of synthesized speech (voice type, frequency, inflection, etc.). Here are examples of vocal rules or styles of an aural CSS:
These examples direct a speech synthesizer (TTS engine) to speak headers in a voice (a kind of “audio font”) called “paid,” on a flat tone, but in a very rich voice. Before speaking the headers, a sound sample will be played from the given URL. Paragraphs with class “heidi” will appear to come from front left (if the sound system is capable of spatial audio), and paragraphs of class “peter” from the right. Paragraphs with class “goat” will be rendered very softly.
Multimodal server application (188) in this example is a user-level, multimodal, server-side computer program that may be implemented with a set of VoiceXML documents which taken together comprise a VoiceXML application. Multimodal server application (188) may be implemented as a web server, implemented in Java, C++, or another language, that supports X+V, SALT, or another multimodal language, by providing responses to HTTP requests from X+V, SALT or other multimodal clients. Multimodal server application (188) may, for a further example, be implemented as a Java server that runs on a Java Virtual Machine (102) and supports a Java voice framework by providing responses to HTTP requests from Java client applications running on multimodal devices. And multimodal server applications that support establishing a multimodal advertising personality for a sponsor of a multimodal application may be implemented in other ways as may occur to those of skill in the art, and all such ways are well within the scope of the present invention.
The voice server in this example includes a speech engine (153). The speech engine is a functional module, typically a software module, although it may include specialized hardware also, that does the work of recognizing and generating human speech. The speech engine (153) includes an automated speech recognition (‘ASR’) engine for speech recognition and a text-to-speech (‘TTS’) engine for generating speech. The speech engine also includes a grammar (104), a lexicon (106), and a language-specific acoustic model (108). The language-specific acoustic model (108) is a data structure, a table or database, for example, that associates SFVs with phonemes representing, to the extent that it is practically feasible to do so, all pronunciations of all the words in a human language. The lexicon (106) is an association of words in text form with phonemes representing pronunciations of each word; the lexicon effectively identifies words that are capable of recognition by an ASR engine.
The grammar (104) communicates to the ASR engine (150) the words and sequences of words that currently may be recognized. For precise understanding, distinguish the purpose of the grammar and the purpose of the lexicon. The lexicon associates with phonemes all the words that the ASR engine can recognize. The grammar communicates the words currently eligible for recognition. The set of words currently eligible for recognition and the set of words capable of recognition may or may not be the same.
Grammars for use in establishing a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention may be expressed in any format supported by any ASR engine, including, for example, the Java Speech Grammar Format (‘JSGF’), the format of the W3C Speech Recognition Grammar Specification (‘SRGS’), the Augmented Backus-Naur Format (‘ABNF’) from the IETF's RFC2234, in the form of a stochastic grammar as described in the W3C's Stochastic Language Models (N-Gram) Specification, and in other grammar formats as may occur to those of skill in the art. Grammars typically operate as elements of dialogs, such as, for example, a VoiceXML <menu> or an X+V<form>.
A grammar's definition may be expressed in-line in a dialog. Or the grammar may be implemented externally in a separate grammar document and referenced from with a dialog with a URI. Here is an example of a grammar expressed in JSFG:
In this example, the elements named <command>, <name>, and <when> are rules of the grammar. Rules are a combination of a rulename and an expansion of a rule that advises an ASR engine which words presently can be recognized. In this example, expansion includes conjunction and disjunction, and the vertical bars ‘|’ mean ‘or.’ An ASR engine processes the rules in sequence, first <command>, then <name>, then <when>. The <command> rule accepts for recognition ‘call’ or ‘phone’ or ‘telephone’ plus, that is, in conjunction with, whatever is returned from the <name> rule and the <when> rule. The <name> rule accepts ‘bob’ or ‘martha’ or ‘joe’ or ‘pete’ or ‘chris’ or ‘john’ or ‘artoush’, and the <when> rule accepts ‘today’ or ‘this afternoon’ or ‘tomorrow’ or ‘next week.’ The command grammar as a whole accepts utterances like these, for example:
The multimodal server application (188) in this example is configured to receive, from a multimodal client located remotely across a network from the voice server, digitized speech for recognition from a user and pass the speech along to the ASR engine (150) for recognition. ASR engine (150) is a module of computer program instructions, also stored in RAM in this example. In carrying out automated speech recognition, the ASR engine receives speech for recognition in the form of at least one digitized word and uses frequency components of the digitized word to derive a Speech Feature Vector (‘SFV’). An SFV may be defined, for example, by the first twelve or thirteen Fourier or frequency domain components of a sample of digitized speech. The ASR engine can use the SFV to infer phonemes for the word from the language-specific acoustic model (108). The ASR engine then uses the phonemes to find the word in the lexicon (106).
Also stored in RAM is a VoiceXML interpreter (192), a module of computer program instructions that processes VoiceXML grammars. VoiceXML input to VoiceXML interpreter (192) may originate from VoiceXML clients running remotely on multimodal devices, from X+V clients running remotely on multimodal devices, or from Java client applications running remotely on multimedia devices. In this example, VoiceXML interpreter (192) interprets and executes VoiceXML segments received from remote multimedia clients and provided to VoiceXML interpreter (192) through multimodal server application (188). Also stored in RAM (168) is a Text To Speech (‘TTS’) Engine (194), a module of computer program instructions that accepts text as input and returns the same text in the form of digitally encoded speech, for use in providing speech as prompts for and responses to users of multimodal systems.
Also stored in RAM (168) is an operating system (154). Operating systems useful in voice servers according to embodiments of the present invention include UNIX™, Linux™, Microsoft NT™, AIX™, IBM's i5/OS™, and others as will occur to those of skill in the art. Operating system (154), multimodal server application (188), VoiceXML interpreter (192), ASR engine (150), JVM (102), and TTS Engine (194) in the example of
Voice server (151) of
Voice server (151) of
The example voice server of
The exemplary voice server (151) of
For further explanation,
In addition to the multimodal sever application (188), the voice server (151) also has installed upon it a speech engine (153) with an ASR engine (150), a grammar (104), a lexicon (106), a language-specific acoustic model (108), and a TTS engine (194), as well as a JVM (102), and a Voice XML interpreter (192). VoiceXML interpreter (192) interprets and executes VoiceXML grammars received from the multimodal device application and provided to VoiceXML interpreter (192) through multimodal server application (188). VoiceXML input to VoiceXML interpreter (192) may originate from the multimodal device application (195) implemented as a VoiceXML client running remotely the multimodal device (152), from the multimodal device application (195) implemented as an X+V client running remotely on the multimodal device (152). As noted above, the multimedia device application (195) also may be implemented as a Java client application running remotely on the multimedia device (152), a SALT application running remotely on the multimedia device (152), and in other ways as may occur to those of skill in the art.
VOIP stands for ‘Voice Over Internet Protocol,’ a generic term for routing speech over an IP-based data communications network. The speech data flows over a general-purpose packet-switched data communications network, instead of traditional dedicated, circuit-switched voice transmission lines. Protocols used to carry voice signals over the IP data communications network are commonly referred to as ‘Voice over IP’ or ‘VOIP’ protocols. VOIP traffic may be deployed on any IP data communications network, including data communications networks lacking a connection to the rest of the Internet, for instance on a private building-wide local area data communications network or ‘LAN.’
Many protocols are used to effect VOIP. The two most popular types of VOIP are effected with the IETF's Session Initiation Protocol (‘SIP’) and the ITU's protocol known as ‘H.323.’ SIP clients use TCP and UDP port 5060 to connect to SIP servers. SIP itself is used to set up and tear down calls for speech transmission. VOIP with SIP then uses RTP for transmitting the actual encoded speech. Similarly, H.323 is an umbrella recommendation from the standards branch of the International Telecommunications Union that defines protocols to provide audio-visual communication sessions on any packet data communications network.
The apparatus of
Multimodal server application (188) provides voice recognition services for multimodal devices by accepting requests for speech recognition and returning speech recognition results, including text representing recognized speech, text for use as variable values in dialogs, and output from execution of semantic interpretation scripts. Multimodal server application (188) includes computer program instructions that provide text-to-speech (‘TTS’) conversion for voice prompts and voice responses to user input in multimodal applications such as, for example, X+V applications, SALT applications, or Java Speech applications.
The multimodal server application (188) receives speech for recognition from a user and passes the speech through API calls to an ASR engine (150) for recognition. The ASR engine receives digitized speech for recognition, uses frequency components of the digitized speech to derive an SPY, uses the SPY to infer phonemes for the word from the language-specific acoustic model (108), and uses the phonemes to find the speech in the lexicon (106). The ASR engine then compares speech founds as words in the lexicon to words in a grammar to determine whether words or phrases in speech are recognized by the ASR engine.
The multimodal server application (188) in this example, in a similar manner to that described above with reference to the system of
The multimodal application in this example may be viewed as a combination of the multimodal server application (188) and a remote multimodal device application (195) cooperating through a VOIP protocol connection (216) to establish a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention. The multimodal device application (195), located on a multimodal device (152) across a network (100) from the voice server (151), is the so-called ‘thin client,’ so-called because much of the functionality for establishing the multimodal advertising personality is implemented on the voice server (151) rather than on the multimodal device (152). The multimodal server application (188) can incorporate a vocal demeanor (550) as a component of a multimodal advertising personality into the multimodal server application by linking one or more markup elements of a markup document of the multimodal server application to one or more styles of a Cascading Style Sheet (‘CSS’) (514) and providing the CSS to a requesting multimodal device application that in turn loads the CSS into a multimodal device application and uses the CSS to control a multimodal user interface, that is, the voice aspects of a multimodal user interface.
Establishing a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention in thick client architectures is generally implemented with multimodal devices, that is, automated computing machinery or computers. In the system of
The example multimodal device (152) of
Also stored in RAM (168) in this example is a multimodal device application (195), a module of computer program instructions capable of operating a multimodal device as an apparatus that supports establishing a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention. The multimodal device application (195) implements speech recognition by accepting speech for recognition from a user and sending the speech for recognition through API calls to the ASR engine (150). The multimodal device application (195) implements speech synthesis generally by sending words to be used as prompts for a user to the TTS engine (194). As an example of thick client architecture, the multimodal device application (195) in this example does not send speech for recognition across a network to a voice server for recognition, and the multimodal device application (195) in this example does not receive synthesized speech, TTS prompts and responses, across a network from a voice server. All grammar processing, voice recognition, and text to speech conversion in this example is performed in an embedded fashion in the multimodal device (152) itself.
More particularly, multimodal device application (195) in this example is a user-level, multimodal, client-side computer program that provides a speech interface through which a user may provide oral speech for recognition through microphone (176), have the speech digitized through an audio amplifier (185) and a coder/decoder (‘codec’) (183) of a sound card (174) and provide the digitized speech for recognition to ASR engine (150). The multimodal device application (195) may be implemented as a set or sequence of X+V documents executing in a multimodal browser (196) or microbrowser that passes VoiceXML grammars and digitized speech through API calls directly to an embedded VoiceXML interpreter (192) for processing. The embedded VoiceXML interpreter (192) may in turn issue requests for speech recognition through API calls directly to the embedded ASR engine (150). Multimodal device application (195) also can provide speech synthesis, TTS conversion, by API calls to the embedded TTS engine (194) for voice prompts and voice responses to user input.
In a further class of exemplary embodiments, the multimodal device application (195) may be implemented as a Java voice application that executes on Java Virtual Machine (102) and calls the ASR engine (150) and the TTS engine (194) directly through APIs for speech recognition and speech synthesis services. In further exemplary embodiments, the multimodal device application (195) may be implemented as a set or sequence of SALT documents executed on a multimodal browser (196) or microbrowser that calls the ASR engine (150) and the TTS engine (194) through APIs for speech recognition and speech synthesis services. In addition to X+V, SALT, and Java implementations, multimodal device application (195) may be implemented in other technologies as will occur to those of skill in the art, and all such implementations are well within the scope of the present invention.
The multimodal device application (195) in this example is configured to establish a multimodal advertising personality for a sponsor of a multimodal application according to embodiments of the present invention by associating one or more vocal demeanors (550) with a sponsor (503) of a multimodal application and presenting a speech portion of the multimodal application for the sponsor using at least one of the vocal demeanors associated with the sponsor. According to embodiments of the present invention, a sponsor may purchase from an owner of the multimodal application exclusive use of a vocal demeanor within the multimodal application. Alternatively, a sponsor may purchase from an owner of the multimodal application exclusive use of a set of vocal demeanors within the multimodal application, including a right to exclude from use within a portion of the multimodal application all vocal demeanors not in the set of vocal demeanors. The multimodal application may select, among the set of vocal demeanors, a vocal demeanor for presentation of a speech portion of the multimodal application for the sponsor in dependence upon sponsor-provided rules. In addition to such use of a vocal demeanor, establishing a multimodal advertising personality according to embodiments of the present invention may also include purchasing by a sponsor from an owner of the multimodal application exclusive use of one or more visual demeanors within the multimodal application; associating one or more visual demeanors with the sponsor of a multimodal application; and presenting a visual portion of the multimodal application for the sponsor using at least one of the visual demeanors associated with the sponsor.
The multimodal device application (195) can incorporate a vocal demeanor (550) as a component of a multimodal advertising personality into the multimodal server application by linking one or more markup elements of a markup document of the multimodal server application to one or more styles of a Cascading Style Sheet (‘CSS’) (514), loading the CSS into the multimodal device application (195), and using the CSS to control a multimodal user interface, that is, the voice aspects of a multimodal user interface. The multimodal device application (195) in this example, running on a stand-alone multimodal device (152) with no network, no VOIP connection, and no voice server containing a remote speech engine or a remote multimodal server application, is an example of a so-called ‘thick client,’ so-called because all of the functionality for establishing the multimodal advertising personality is implemented on the multimodal device itself.
For further explanation,
The method of
A vocal demeanor defines the speaking voice of a multimodal application for one or more voice prompts. The voice prompts are speech output of a multimodal application produced by a speech synthesizer or TTS engine under multimodal application program control. The TTS engine uses a standard voice model to generate digitized speech for output to a user, and alters the output of the voice model according to selected styles of a CSS to produce voice output conforming to a vocal demeanor. The voice output conforms to the vocal demeanor because the CSS and therefore the styles of the CSS that govern the alternations of the standard voice model are chosen to generate voice output that accords with vocal attributes of the vocal demeanor. Such vocal attributes may include, for example, speech rate, voice family, pitch, pitch range, stress, and richness. A combination of such vocal attributes is defined by each vocal demeanor. Such combinations can produce voices such as: Energetic Female, Tired Female, Normal Female, Low Pitch Female, Higher Pitch Female, Energetic Male, Tired Male, Normal Male, Low Pitch Male, Higher Pitch Male, and so on, as will occur to those of skill in the art.
As mentioned, vocal attributes defining a vocal demeanor may include, for example, speech rate, voice family, pitch, pitch range, stress, and richness. Speech rate is speaking rate for prompts in words per minute. Voice family represents in effect a font for speech, describing the overall nature and timbre of a voice either in generic terms, male, female, child, or in specific terms, Mary's voice, Jack's voice, and so on. The name of a voice family may be viewed as identifying a vocal font for a vocal demeanor. Pitch is the average frequency of a speaking voice for prompts. Voice family may be related to pitch: An average pitch for a male voice is typically about 120 Hertz, while an average pitch for a female voice is typically about 210 Hertz.
Pitch range is a measure of variation in average pitch. The perceived pitch of a voice is determined by its fundamental frequency and typically has a value of about 120 Hz for a male voice and about 210 Hz for a female voice. Human languages are spoken with varying inflection and pitch—variations that convey additional meaning and emphasis. A highly animated voice, that is, a voice that is heavily inflected, displays a high pitch range. Pitch range specifies the range over which these variations may occur in voice prompts, that is, how much the fundamental frequency may deviate from the average pitch. Pitch range defines the amount of inflection in a vocal prompt. A low pitch range value indicates a monotone prompt; a high pitch range value identifies an animated voice prompt. A medium pitch range value indicates normal inflection.
Richness is a measure of the brightness of a voice prompt. A rich voice will ‘carry’ in a large room; a smooth voice carries less well. The term ‘smooth’ refers to how a waveform of the voice looks when drawn. A rich voice has a higher ratio of peak amplitude values to average amplitude values than a smooth voice. A rich voice is more ‘condensed’ in effect than a smooth voice.
In this example of
The method of
In addition to an exclusive interest to a particular vocal demeanor, a sponsor may also be concerned to exclude from use within a portion of the multimodal application all vocal demeanors not in a set of vocal demeanors. A multimodal application may be viewed as a tree with an XHTML document at the root and hyperlinks within the root document leading to branch documents and leaf documents in the tree. Consider the example of links from frame (706). Such links are likely to be considered part of the advertising content of the sponsor of frame (706). Such links may lead to subtrees of the multimodal application (712-722) that are particularly pertinent to the interests of the sponsor of frame (706), a home website, sales data input screens, contact information screens, and so on. On such screens, the sponsor of frame (706) may wish to exclude all vocal demeanors not in a set purchased by the sponsor of frame (706), so that all such screens or frames present to users the same overall vocal demeanor—or a coherent set of vocal demeanors chosen by the sponsor. In this circumstance, a sponsor can purchase from an owner of the multimodal application exclusive use of a set of vocal demeanors within the multimodal application, including a right to exclude from use within a portion of the multimodal application all vocal demeanors not in the set of vocal demeanors.
Vocal demeanors may be predefined and implemented as computer data structures having data elements representing vocal characteristics, lists of computer data, objects instantiated from demeanor classes in an object-oriented programming language, records in tables of a database, and so on. A vocal demeanor is not necessarily the only component of a multimodal advertising personality. A multimodal advertising personality may include visual aspects, implemented for example with a visual demeanor, as well. Visual demeanor is the overall visual appearance of a multimodal application, background colors, text colors, text fonts, selection and placement of graphic elements, and so on. Visual demeanor may be characterized by attributes such as age (vibrant colors for young users, quieter colors for mature users), gender (sans serif fonts for women, serifs for men), location (Eiffel Tower background for Parisians, the Alamo for Texans), time (bright color palettes in the morning, quieter palettes in the evening), application domain (more text for legal subjects, more graphics for architectural subjects), and so on as will occur to those of skill in the art.
Again with reference to
In this example X+V page, a VoiceXML form identified as “drinkform” voice enables an XHTML input form named “fid.” The table data field named “in1” registers “drinkform” as an event handler for “focus” events in the field; that is, when field “in1” gains focus, the multimodal application calls “drinkform” to administer vocal input to field “in1.” By use of the <drinks> grammar:
This example X+V page shows a link, defined as a <link> element, to an external CSS identified by the URL “http://www.ibmcom/style/demeanor.jsp”:
This example X+V page defines a multimodal speech dialog as a VoiceXML <vxml:form> element with id=“drinkform.” The <vxml:form> element includes a prompt <vxml:prompt src=“#p1”> that refers to an <h2> heading element:
identified as id=“p1.” The <h2> heading element is controlled by a class attribute, class=“server,” that identifies the style to be returned from the reference to the external CSS, “demeanor.jsp.” The value of the style returned may be, for example:
signifying that the spoken prompt for the <h2> heading is to be rendered in a female voice, and any prompts for <h3> headings are to be rendered in a male voice. Specific demeanor attributes may be implemented for example as session attributes of a logon session, or as attributes that persist even across sessions in a persistent user profile. Session-specific attributes may be passed as a cookie in the header of an HTTP request for the CSS. Analogous schemes as may occur to those of skill in the art can be constructed for the generation of grammars and the vocabulary used in prompts.
The fact that the referenced CSS is named “demeanor.jsp” indicates that the external CSS is returned from the computation of a Java Server Page. This effectively makes the referenced external CSS a variable. The multimodal application, through its operating environment, a browser or a JVM, can select and return a CSS whose styles effect the selected vocal demeanor. The vocal demeanor typically is selected to match evaluated attributes of user interaction, as described in more detail above. A CSS can be selected from among many CSSes, hundreds or thousands, according to the characteristics of a matching demeanor, age, gender, location, application domain, speech rate, voice family, pitch, pitch range, richness, and so on. Returning a selected CSS, loading it into the multimodal application, and using it to govern the presentation of the user interface, speech aspects in particular, is an example of an effective way of presenting a speech portion of the multimodal application for the sponsor using at least one of the vocal demeanors associated with the sponsor in establishing a multimodal advertising personality for a sponsor of a multimodal application.
For further explanation,
The method of
In these examples, the formation of the rules includes user characteristics, but the advertising methodology is still oriented to the sponsor because the sponsor sets the rules for selection of vocal demeanors in establishing a multimodal advertising personality.
For further explanation,
The method of
The method of
The <h2> heading element:
is controlled by a class attribute, class=“server,” that identifies the style to be returned from the reference to the external CSS, “demeanor.jsp.” The value of the style returned may be, for example:
signifying that <h2> headings that reference class=“server” have visual demeanor set to the color red for text display, background color yellow, and bold font. <h3> headings all have their visual demeanor set to black text, white background, and normal font.
For further explanation,
The UML model of
Exemplary embodiments of the present invention are described largely in the context of a fully functional computer system for establishing a multimodal advertising personality for a sponsor of a multimodal application. Readers of skill in the art will recognize, however, that the present invention also may be embodied in a computer program product disposed on signal bearing media for use with any suitable data processing system. Such signal bearing media may be transmission media or recordable media for machine-readable information, including magnetic media, optical media, or other suitable media. Examples of recordable media include magnetic disks in hard drives or diskettes, compact disks for optical drives, magnetic tap; and others as will occur to those of skill in the art. Examples of transmission media include telephone data communications networks for voice communications and digital data communications data communications networks such as, for example, Ethernets™ and data communications networks that communicate with the Internet Protocol and the World Wide Web. Persons skilled in the art will immediately recognize that any computer system having suitable programming means will be capable of executing the steps of the method of the invention as embodied in a program product. Persons skilled in the art will recognize immediately that, although some of the exemplary embodiments described in this specification are oriented to software installed and executing on computer hardware, nevertheless, alternative embodiments implemented as firmware or as hardware are well within the scope of the present invention.
It will be understood from the foregoing description that modifications and changes may be made in various embodiments of the present invention without departing from its true spirit. The descriptions in this specification are for purposes of illustration only and are not to be construed in a limiting sense. The scope of the present invention is limited only by the language of the following claims.
This application claims the benefit as a continuation application under 35 U.S.C. §120 of U.S. patent application Ser. No. 13/535,588 filed Jun. 28, 2012 and entitled “Establishing a Multimodal Advertising Personality for a Sponsor of a Multimodal Application,” which is a continuation of U.S. patent application Ser. No. 13/095,037 filed Apr. 27, 2011 and entitled “Establishing a Multimodal Advertising Personality for a Sponsor of a Multimodal Application,” issued as U.S. Pat. No. 8,239,205, which is a continuation of U.S. patent application Ser. No. 11/530,921 filed Sep. 12, 2006 and entitled “Establishing a Multimodal Advertising Personality for a Sponsor of a Multimodal Application,” issued as U.S. Pat. No. 7,957,976, the entire contents of all of which are incorporated herein by reference.
| Number | Name | Date | Kind |
|---|---|---|---|
| 4624012 | Lin et al. | Nov 1986 | A |
| 5375164 | Jennings | Dec 1994 | A |
| 5553119 | McAllister et al. | Sep 1996 | A |
| 5577165 | Takebayashi et al. | Nov 1996 | A |
| 5584052 | Gulau et al. | Dec 1996 | A |
| 5842167 | Miyatake et al. | Nov 1998 | A |
| 5857171 | Kageyama et al. | Jan 1999 | A |
| 5860064 | Henton | Jan 1999 | A |
| 5933802 | Emori | Aug 1999 | A |
| 5969717 | Ikemoto | Oct 1999 | A |
| 5970455 | Wilcox et al. | Oct 1999 | A |
| 5987415 | Breese et al. | Nov 1999 | A |
| 6081781 | Tanaka et al. | Jun 2000 | A |
| 6098043 | Forest et al. | Aug 2000 | A |
| 6144938 | Surace et al. | Nov 2000 | A |
| 6173262 | Hirschberg | Jan 2001 | B1 |
| 6208972 | Grant et al. | Mar 2001 | B1 |
| 6240170 | Shaffer et al. | May 2001 | B1 |
| 6243375 | Speicher | Jun 2001 | B1 |
| 6266400 | Castagna | Jul 2001 | B1 |
| 6275806 | Pertrushin | Aug 2001 | B1 |
| 6301560 | Masters | Oct 2001 | B1 |
| 6344103 | Cheng et al. | Feb 2002 | B1 |
| 6385584 | McAllister et al. | May 2002 | B1 |
| 6513011 | Uwakubo | Jan 2003 | B1 |
| 6606599 | Grant et al. | Aug 2003 | B2 |
| 6708153 | Brittan et al. | Mar 2004 | B2 |
| 6736641 | Quiroz | May 2004 | B2 |
| 6813605 | Nakamura et al. | Nov 2004 | B2 |
| 6842767 | Partovi et al. | Jan 2005 | B1 |
| 6856960 | Dragosh et al. | Feb 2005 | B1 |
| 6920425 | Will et al. | Jul 2005 | B1 |
| 6932668 | Digby et al. | Aug 2005 | B2 |
| 6944592 | Pickering | Sep 2005 | B1 |
| 6950799 | Bi et al. | Sep 2005 | B2 |
| 6983252 | Matheson et al. | Jan 2006 | B2 |
| 6999930 | Roberts et al. | Feb 2006 | B1 |
| 7035805 | Miller | Apr 2006 | B1 |
| 7091976 | Ostermann et al. | Aug 2006 | B1 |
| 7171243 | Watanabe et al. | Jan 2007 | B2 |
| 7188067 | Grant et al. | Mar 2007 | B2 |
| 7324947 | Jordan et al. | Jan 2008 | B2 |
| 7330890 | Partovi et al. | Feb 2008 | B1 |
| 7340389 | Vargas | Mar 2008 | B2 |
| 7346153 | Lewis et al. | Mar 2008 | B2 |
| 7349527 | Yacoub et al. | Mar 2008 | B2 |
| 7356470 | Roth et al. | Apr 2008 | B2 |
| 7363029 | Othmer | Apr 2008 | B2 |
| 7376586 | Partovi et al. | May 2008 | B1 |
| 7386450 | Baumgartner et al. | Jun 2008 | B1 |
| 7409349 | Wang et al. | Aug 2008 | B2 |
| 7412422 | Shiloh | Aug 2008 | B2 |
| 7454348 | Kapilow et al. | Nov 2008 | B1 |
| 7487085 | Ativanichayaphong et al. | Feb 2009 | B2 |
| 7509659 | McArdle | Mar 2009 | B2 |
| 7552403 | Wilson | Jun 2009 | B2 |
| 7640160 | Di Cristo et al. | Dec 2009 | B2 |
| 7693719 | Chu et al. | Apr 2010 | B2 |
| 7729916 | Coffman et al. | Jun 2010 | B2 |
| 7949526 | Ju et al. | May 2011 | B2 |
| 7957976 | Cross, Jr. et al. | Jun 2011 | B2 |
| 8005729 | Ulm et al. | Aug 2011 | B1 |
| 8073697 | Cross, Jr. et al. | Dec 2011 | B2 |
| 8145493 | Cross, Jr. et al. | Mar 2012 | B2 |
| 8150698 | Ativanichayaphong et al. | Apr 2012 | B2 |
| 8239205 | Cross, Jr. et al. | Aug 2012 | B2 |
| 20020007276 | Rosenblatt et al. | Jan 2002 | A1 |
| 20020049594 | Moore et al. | Apr 2002 | A1 |
| 20020065944 | Hickey et al. | May 2002 | A1 |
| 20020092019 | Marcus | Jul 2002 | A1 |
| 20020099553 | Brittan et al. | Jul 2002 | A1 |
| 20020120554 | Vega | Aug 2002 | A1 |
| 20020147593 | Lewis et al. | Oct 2002 | A1 |
| 20020184610 | Chong et al. | Dec 2002 | A1 |
| 20030023442 | Akabane et al. | Jan 2003 | A1 |
| 20030039341 | Burg et al. | Feb 2003 | A1 |
| 20030046316 | Gergic et al. | Mar 2003 | A1 |
| 20030046346 | Mumick et al. | Mar 2003 | A1 |
| 20030088415 | Kobal et al. | May 2003 | A1 |
| 20030101451 | Bentolila et al. | May 2003 | A1 |
| 20030125945 | Doyle | Jul 2003 | A1 |
| 20030179865 | Stillman et al. | Sep 2003 | A1 |
| 20030182622 | Sibal et al. | Sep 2003 | A1 |
| 20030195739 | Washio | Oct 2003 | A1 |
| 20030217161 | Balasuriya | Nov 2003 | A1 |
| 20030229900 | Reisman | Dec 2003 | A1 |
| 20030235282 | Sichelman et al. | Dec 2003 | A1 |
| 20040019487 | Kleindienst et al. | Jan 2004 | A1 |
| 20040025115 | Sienel et al. | Feb 2004 | A1 |
| 20040031058 | Reisman | Feb 2004 | A1 |
| 20040044516 | Kennewick et al. | Mar 2004 | A1 |
| 20040049390 | Brittan et al. | Mar 2004 | A1 |
| 20040059705 | Wittke et al. | Mar 2004 | A1 |
| 20040083109 | Halonen et al. | Apr 2004 | A1 |
| 20040120472 | Popay et al. | Jun 2004 | A1 |
| 20040120476 | Harrison et al. | Jun 2004 | A1 |
| 20040138890 | Ferrans et al. | Jul 2004 | A1 |
| 20040148346 | Weaver et al. | Jul 2004 | A1 |
| 20040153323 | Charney et al. | Aug 2004 | A1 |
| 20040179038 | Blattner et al. | Sep 2004 | A1 |
| 20040215451 | Macleod | Oct 2004 | A1 |
| 20040215453 | Orbach | Oct 2004 | A1 |
| 20040216036 | Chu et al. | Oct 2004 | A1 |
| 20040236574 | Ativanichayaphong et al. | Nov 2004 | A1 |
| 20040260562 | Kujirai | Dec 2004 | A1 |
| 20050049860 | Junqua et al. | Mar 2005 | A1 |
| 20050075884 | Badt | Apr 2005 | A1 |
| 20050091059 | Lecoeuche | Apr 2005 | A1 |
| 20050131701 | Cross et al. | Jun 2005 | A1 |
| 20050137862 | Monkowski | Jun 2005 | A1 |
| 20050138219 | Bou-Ghannam et al. | Jun 2005 | A1 |
| 20050138647 | Bou-ghannam et al. | Jun 2005 | A1 |
| 20050154580 | Horowitz et al. | Jul 2005 | A1 |
| 20050160461 | Baumgartner et al. | Jul 2005 | A1 |
| 20050188412 | Dacosta | Aug 2005 | A1 |
| 20050203729 | Roth et al. | Sep 2005 | A1 |
| 20050203747 | Lecoeuche | Sep 2005 | A1 |
| 20050261908 | Cross et al. | Nov 2005 | A1 |
| 20050273769 | Eichenberger et al. | Dec 2005 | A1 |
| 20050283367 | Ativanichayaphong et al. | Dec 2005 | A1 |
| 20060047510 | Ativanichayaphong et al. | Mar 2006 | A1 |
| 20060064302 | Ativanichayaphong et al. | Mar 2006 | A1 |
| 20060069564 | Allison et al. | Mar 2006 | A1 |
| 20060074672 | Allefs | Apr 2006 | A1 |
| 20060074680 | Cross et al. | Apr 2006 | A1 |
| 20060075120 | Smit | Apr 2006 | A1 |
| 20060111906 | Cross et al. | May 2006 | A1 |
| 20060122836 | Cross et al. | Jun 2006 | A1 |
| 20060123358 | Lee et al. | Jun 2006 | A1 |
| 20060136222 | Cross et al. | Jun 2006 | A1 |
| 20060136228 | Lin | Jun 2006 | A1 |
| 20060146728 | Engelsma et al. | Jul 2006 | A1 |
| 20060168095 | Sharma et al. | Jul 2006 | A1 |
| 20060168595 | McArdle | Jul 2006 | A1 |
| 20060184626 | Agapi et al. | Aug 2006 | A1 |
| 20060190264 | Jaramillo et al. | Aug 2006 | A1 |
| 20060218039 | Johnson | Sep 2006 | A1 |
| 20060229880 | White et al. | Oct 2006 | A1 |
| 20060235694 | Cross et al. | Oct 2006 | A1 |
| 20060287845 | Cross et al. | Dec 2006 | A1 |
| 20060287865 | Cross et al. | Dec 2006 | A1 |
| 20060287866 | Cross et al. | Dec 2006 | A1 |
| 20060288309 | Cross et al. | Dec 2006 | A1 |
| 20070118378 | Skuratovsky | May 2007 | A1 |
| 20070265851 | Ben-David et al. | Nov 2007 | A1 |
| 20070274296 | Cross et al. | Nov 2007 | A1 |
| 20070274297 | Cross et al. | Nov 2007 | A1 |
| 20070288241 | Cross et al. | Dec 2007 | A1 |
| 20070294084 | Cross et al. | Dec 2007 | A1 |
| 20080065387 | Cross, Jr. et al. | Mar 2008 | A1 |
| 20080065389 | Cross et al. | Mar 2008 | A1 |
| 20080065390 | Ativanichayaphong et al. | Mar 2008 | A1 |
| 20080086564 | Putman et al. | Apr 2008 | A1 |
| 20080140410 | Ativanichayaphong et al. | Jun 2008 | A1 |
| 20080162136 | Agapi et al. | Jul 2008 | A1 |
| 20080177530 | Cross et al. | Jul 2008 | A1 |
| 20080195393 | Cross et al. | Aug 2008 | A1 |
| 20080208584 | Ativanichayaphong et al. | Aug 2008 | A1 |
| 20080208585 | Ativanichayaphong et al. | Aug 2008 | A1 |
| 20080208586 | Ativanichayaphong et al. | Aug 2008 | A1 |
| 20080208587 | Ben-David et al. | Aug 2008 | A1 |
| 20080208589 | Cross et al. | Aug 2008 | A1 |
| 20080208590 | Cross et al. | Aug 2008 | A1 |
| 20080208591 | Ativanichayaphong et al. | Aug 2008 | A1 |
| 20080208592 | Cross et al. | Aug 2008 | A1 |
| 20080208593 | Ativanichayaphong et al. | Aug 2008 | A1 |
| 20080208594 | Cross et al. | Aug 2008 | A1 |
| 20080228494 | Cross | Sep 2008 | A1 |
| 20080228495 | Cross, Jr. et al. | Sep 2008 | A1 |
| 20080235021 | Cross et al. | Sep 2008 | A1 |
| 20080235022 | Bergl et al. | Sep 2008 | A1 |
| 20080235027 | Cross | Sep 2008 | A1 |
| 20080235029 | Cross et al. | Sep 2008 | A1 |
| 20080249782 | Ativanichayaphong et al. | Oct 2008 | A1 |
| 20080255850 | Cross et al. | Oct 2008 | A1 |
| 20080255851 | Ativanichayaphong et al. | Oct 2008 | A1 |
| 20100057443 | Di Cristo et al. | Mar 2010 | A1 |
| 20100123002 | Caporicci | May 2010 | A1 |
| 20120046953 | Cross, Jr. et al. | Feb 2012 | A1 |
| 20120151326 | Cross, Jr. et al. | Jun 2012 | A1 |
| 20120271642 | Cross, Jr. et al. | Oct 2012 | A1 |
| Number | Date | Country |
|---|---|---|
| 1385783 | Dec 2002 | CN |
| 1564123 | Jan 2005 | CN |
| 0794670 | Sep 1997 | EP |
| 1450350 | Aug 2004 | EP |
| 2000155529 | Jun 2000 | JP |
| 2003140672 | May 2003 | JP |
| WO 9948088 | Sep 1999 | WO |
| WO 0051106 | Aug 2000 | WO |
| WO 0232140 | Apr 2002 | WO |
| WO 2004062945 | Jul 2004 | WO |
| WO 2006108795 | Oct 2006 | WO |
| Entry |
|---|
| Axelsson, et al.; “XHTML+Voice Profile 1.2” Internet, [Online] Mar. 16, 2004 (Mar. 6, 2004), pp. 1-53, XP002484188 Retrieved from the Internet: URL: http://www.voicexml.org/specs/mutlimodal/x+v/12/spec.html [retrieved on Jun. 12, 2008]. |
| W3C: “Voice Extensible Markup Language (VoiceXML) Version 2.0” Internet Citation, [Online] XP002248286 Retrieved from the Internet: URL:http://www.w3.org/TR/voicexml20 [retrieved on Jul. 18, 2003]. |
| W3C: “Voice Extensible Markup Language (VoiceXML) 2.1, W3C Candidate Recommendation Jun. 13, 2005” Internet, [Online] Jun. 13, 2005 (2005-16-13), pp. 1-34, XP002484189 Retrieved from the Internet: URL:http://www.w3.org/TR/2005/CR-voicexml21-20050613/ [retrieved on Jun. 12, 2008]. |
| PCT Search Report, Jun. 25, 2008; PCT Application No. PCT/EP2008/051358. |
| PCT Search Report, Jun. 18, 2008; PCT Application No. PCT/EP2008/051363. |
| Didier Guillevic, et al., Robust Semantic Confidence Scoring ICSLP 2002: 7.sup.th International Conference On Spoken Language Processing. Denver Colorado, Sep. 16-20, 2002 International Conference on Spoken Language Processing (ICSLP), Adelaide: Causal Productions, AI, Sep. 16, 2002, p. 853, XP007011561 ISBN:9788-1-876346-40-9. |
| U.S. Appl. No. 10/919,005, filed Dec. 2005, Eichenberger et al. |
| U.S. Appl. No. 12/109,151, filed Apr. 2008, Agapi et al. |
| U.S. Appl. No. 12/109,167, filed Apr. 2008, Agapi et al. |
| U.S. Appl. No. 12/109,204, filed Apr. 2008, Agapi et al. |
| U.S. Appl. No. 12/109,227, filed Apr. 2008, Agapi et al. |
| U.S. Appl. No. 12/109,214, filed Apr. 2008, Agapi et al. |
| Number | Date | Country | |
|---|---|---|---|
| 20140052449 A1 | Feb 2014 | US |
| Number | Date | Country | |
|---|---|---|---|
| Parent | 13535588 | Jun 2012 | US |
| Child | 13953027 | US | |
| Parent | 13095037 | Apr 2011 | US |
| Child | 13535588 | US | |
| Parent | 11530921 | Sep 2006 | US |
| Child | 13095037 | US |
