Patent Application
20060047508
The present invention relates to a speech processing apparatus and method, and in particular to a technique for restricting use of generated speech data for purposes other than a particular purpose.
There are proposed telephone answering apparatuses which create a voice response message by utilizing a speech synthesis technique. For example, a speech-synthesis telephone answering apparatus described in Japanese Patent Laid-Open No. 63-124653 employs a method in which a response is made by converting a response message sentence, which has been created by an editor, to speech through speech synthesis. This technique is advantageous in that a user can insert his name in the message while keeping his voice unknown to others.
Similar to speech obtained by reproducing recording, there also exists a model speaker for speech synthesis who utters speech which is to be the base of the speech synthesis. In general, manufacturers make a contract with a model speaker which clarifies the purpose of use. In the above example, the purpose is use as a response message of a telephone answering apparatus. However, it is possible to reproduce a response message of a telephone answering apparatus from a speaker for checking. Therefore, it is conceivable that the synthesized speech reproduced from a speaker is used for other purposes. Accordingly, the manufactures are required to take measures to prevent the speech from being used for other purposes. It goes without saying that similar measures must be taken for the voice response message prepared for a telephone set in advance.
As an example of other conventional techniques related to the present invention, there is a technique described in Japanese Patent Laid-Open No. 02-68773. In this document, there is disclosed an audio signal reproduction apparatus which generates noise consisting of high-frequency band components among non-audio-frequency bands and adds the noise on an analog audio signal of an audio-frequency band for the purpose of improving sound quality. In this document, however, there is no description nor suggestion at all about generating noise consisting of audio-frequency band components and adding the noise on a speech to prevent a voice response message from being used for purposes other than an intended purpose.
The speech-synthesis telephone answering apparatus in Japanese Patent Laid-Open No. 63-124653 has a lot of merits to be enjoyed by users. However, it has a problem that, though the main purpose is use as a response message of a telephone, use for purposes other than an intended purpose is easily possible because any message can be created.
In view of the above problems in the conventional art, the present invention has an object to prevent generated speech data from being used for purposes other than a particular purpose.
In one aspect of the present invention, a speech processing apparatus having communication means, includes acquisition means for acquiring speech data, addition means for adding predetermined audio data within audio-frequency band excluding predetermined frequency band, to the speech data acquired by the acquisition means, and band limiting means for limiting the speech data to which the predetermined audio data has been added by the addition means, to the predetermined frequency band, wherein the communication means sends the speech data which has been limited to the predetermined frequency band by the band limiting means.
The above and other objects and features of the present invention will appear more fully hereinafter from a consideration of the following description taken in connection with the accompanying drawing wherein one example is illustrated by way of example.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention, and together with the description, serve to explain the principles of the invention.
Preferred embodiment(s) of the present invention will be described in detail in accordance with the accompanying drawings. The present invention is not limited by the disclosure of the embodiments and all combinations of the features described in the embodiments are not always indispensable to solving means of the present invention.
In
For a telephone answering apparatus, it is necessary to take measures for preventing the speech output function of the telephone answering apparatus from being used for purposes other than the purpose of outputting a response message, as described above. In this case, the response message is a message transmitted to a call originator via a telephone line (the public line network 111). Therefore, if it is output not via a telephone line,.the use can be determined to be for a purpose other than the originally intended purpose. Accordingly, in this embodiment, noise as a particular sound signal within audio-frequency bands excluding telephone-frequency bands is added on the speech signal of a response message. The “noise” stated here may be a single frequency tone or a tone including multiple frequency components only if it is within the audio-frequency bands excluding the telephone-frequency bands. When a response message with such noise added is transmitted via a telephone line, the noise is not heard. However, when a telephone line is not used (that is, when the use is considered to be for a purpose other than the originally intended purpose), the noise is heard. Thereby, use for purposes other than the originally intended purpose can be prevented.
In the configuration shown in
In this case, the bands used by the public line network 111 are the telephone-frequency bands. Therefore, the pass band of the band limiting filter is generally set between 300 Hz and 3.4 kHz. Meanwhile, the digital speech signal handled in this apparatus has an audio-frequency band, that is, a band between 300 Hz to 20 kHz.
In this figure, an input maintainer 201 maintains a message sentence for a speech response, which has been input by a user via the input device 105. A speech synthesizer 202 converts the message sentence maintained by the input maintainer 201 to speech by means of speech synthesis. As described above, the synthesized speech obtained here has an audio-frequency band, that is a band between 300 Hz to 20 kHz. A speech maintainer 203 maintains the speech generated by the speech synthesizer 202. A noise generator 204 generates noise consisting of frequency components within the audio-frequency bands excluding the telephone-frequency bands (for example, between 4 kHz and 20 kHz). A noise maintainer 205 maintains the noise generated by the noise generator 204. An adder 206 adds the speech maintained by the speech maintainer 203 and the noise maintained by a noise maintainer 205 to generate noise-added speech. A noise-added speech maintainer 207 maintains the noise-added speech generated by the adder 206.
First, at step S301, the speech synthesizer 202 converts a response message sentence maintained by the input maintainer 201 to speech data. The synthesized speech data generated here has a band between 300 Hz and 20 kHz, as described above. The synthesized speech data is maintained by the speech maintainer 203.
At the next step S302, the noise generator 204 generates noise consisting of frequency components which are beyond the usable bands but within the audio-frequency bands (for example, between 4 kHz to 20 kHz). The noise is maintained by the noise maintainer 205, and the process proceeds to step S303.
At step S303, the adder 206 adds the speech maintained by the speech maintainer 203 and the noise maintained by the noise maintainer 205. The obtained noise-added speech is maintained by the noise-added speech maintainer 207, and the process proceeds to step S304.
At step S304, the noise-added speech maintained by the noise-added speech maintainer 207 is input in the D/A converter 107 and converted to an analog signal, and then, it passes through the band limiting filer 107a. Then, at step 305, the noise-added speech which has passed the band limiting filter 107a is sent by the communication device 108 to a call originator via the public line network 111, and the process ends.
All the processings performed before the conversion by the D/A converter is performed at step S304 are processings in which a digital signal is handled. This configuration is significantly different from that of the audio signal reproduction apparatus described in Japanese Patent Laid-Open No. 2-68773 which requires generation and adding of an analog noise and, therefore, cannot add noise before the D/A converter.
According to the speech output process described above, if a noise-added speech as a response message is transmitted via the public line network 111 to return the response message to a call originator, the noise component of the noise-added speech is suppressed by the band limiting filer 107a, and therefore the noise is not perceived. Meanwhile, if the noise-added speech is used not via the public line network 111, the added noise is not removed, and therefore the noise is perceived. Thus, it is possible to prevent use of a response message for purposes other than the originally intended purpose.
Though description has been made on a case where speech synthesis is employed in the embodiment described above, the present invention is not limited thereto and is applicable to the configuration in which speech recorded in advance is used. In this case, the input maintainer 201 and the speech synthesizer 202 in
Since the embodiment described above is based on the assumption that a telephone line (the public line network 111) is used as communication means, and therefore, description has been made on a case where the telephone-frequency bands are considered to be the usable bands. However, the present invention is not limited thereto. That is, band limitation may be imposed depending on communication means used for communication with an external apparatus.
Note that the present invention can be applied to an apparatus comprising a single device or to system constituted by a plurality of devices.
Furthermore, the invention can be implemented by supplying a software program, which implements the functions of the foregoing embodiments, directly or indirectly to a system or apparatus, reading the supplied program code with a computer of the system or apparatus, and then executing the program code. In this case, so long as the system or apparatus has the functions of the program, the mode of implementation need not rely upon a program.
Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the claims of the present invention also cover a computer program for the purpose of implementing the functions of the present invention.
In this case, so long as the system or apparatus has the functions of the program, the program may be executed in any form, such as an object code, a program executed by an interpreter, or scrip data supplied to an operating system.
Example of storage media that can be used for supplying the program are a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a CD-RW, a magnetic tape, a non-volatile type memory card, a ROM, and a DVD (DVD-ROM and a DVD-R).
As for the method of supplying the program, a client computer can be connected to a website on the Internet using a browser of the client computer, and the computer program of the present invention or an automatically-installable compressed file of the program can be downloaded to a recording medium such as a hard disk. Further, the program of the present invention can be supplied by dividing the program code constituting the program into a plurality of files and downloading the files from different websites. In other words, a WWW (World Wide Web) server that downloads, to multiple users, the program files that implement the functions of the present invention by computer is also covered by the claims of the present invention.
It is also possible to encrypt and store the program of the present invention on a storage medium such as a CD-ROM, distribute the storage medium to users, allow users who meet certain requirements to download decryption key information from a website via the Internet, and allow these users to decrypt the encrypted program by using the key information, whereby the program is installed in the user computer.
Besides the cases where the aforementioned functions according to the embodiments are implemented by executing the read program by computer, an operating system or the like running on the computer may perform all or a part of the actual processing so that the functions of the foregoing embodiments can be implemented by this processing.
Furthermore, after the program read from the storage medium is written to a function expansion board inserted into the computer or to a memory provided in a function expansion unit connected to the computer, a CPU or the like mounted on the function expansion board or function expansion unit performs all or a part of the actual processing so that the functions of the foregoing embodiments can be implemented by this processing.
As many apparently widely different embodiments of the present invention can be made without departing from the spirit and scope thereof, it is to be understood that the invention is not limited to the specific embodiments thereof except as defined in the appended claims.
This application claims priority from Japanese Patent Application No. 2004-249015 filed on Aug. 27, 2004, the entire contents of which are hereby incorporated by reference herein.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2004-249015 | Aug 2004 | JP | national |
