Speech recognition system, speech recognition method, speech synthesis system, speech synthesis method, and program product
The object of the present invention is to keep a high success rate in recognition with a low-volume of sound signal, without being affected by noise. The speech recognition system comprises a sound signal processor 10 configured to acquire a sound signal, and to calculate a sound signal parameter based on the acquired sound signal; an electromyographic signal processor 13 configured to acquire potential changes on a surface of the object as an electromyographic signal, and to calculate an electromyographic signal parameter based on the acquired electromyographic signal; an image information processor 16 configured to acquire image information by taking an image of the object, and to calculate an image information parameter based on the acquired image information; a speech recognizer 20 configured to recognize a speech signal vocalized by the object, based on the sound signal parameter, the electromyographic signal parameter and the image information parameter; and a recognition result provider 21 configured to provide a result recognized by the speech recognizer 20.
1. A speech synthesis system, comprising:
a sound signal acquirer configured to acquire a sound signal including a speech signal vocalized by a speaker and a noise signal;
a speech recognizer configured to recognize speech vocalized by the speaker in the speech signal included in the sound signal;
a first spectrum generator configured to generate a spectrum of the sound signal acquired by the sound signal acquirer as a first spectrum;
a second spectrum generator configured to generate a second spectrum, based on features of localized phonemes recognized by the speech recognizer so that the second spectrum does not contain a spectrum of the noise signal;
a modified spectrum generator configured to generate a modified spectrum by multiplying the first spectrum by the second spectrum; and
an outputter configured to output a synthesized speech signal of the vocalized speech based on the modified spectrum.
2. The speech synthesis system according to claim 1 , wherein the outputter comprises a communicator configured to transmit the synthesized speech signal as data.
3. The speech synthesis system according to claim 1 , further comprising an electromyographic signal processor configured to detect and process motion of muscles around a mouth of the speaker when the sound signal is vocalized.
4. A speech synthesis method comprising:
acquiring a sound signal including a speech signal vocalized by a speaker and a noise signal;
recognizing speech vocalized by the speaker in the speech signal included in the sound signal;
generating a spectrum of the acquired sound signal as a first spectrum;
generating a second spectrum based on features of localized phonemes of the recognized speech signal so that the second spectrum does not contain a spectrum of the noise signal;
generating a modified spectrum by multiplying the first spectrum by the second spectrum; and
outputting a synthesized speech signal of the vocalized speech based on the modified spectrum.
5. The speech synthesis method according to claim 4 , further comprising detecting and processing motion of muscles around a mouth of the speaker when the sound signal is vocalized.
6. A computer readable storage medium storing computer executable instructions which when executed by a processor, causes the processor to perform a method of synthesizing a speech signal, the method comprising the steps of:
acquiring a sound signal including a speech signal vocalized by a speaker and a noise signal;
recognizing speech vocalized by the speaker in the speech signal included in the sound signal;
generating a spectrum of the acquired sound signal as a first spectrum;
generating a second spectrum based on the features of the localized phonemes of the recognized speech signal so that the second spectrum does not contain a spectrum of the noise signal;
generating a modified spectrum by multiplying the first spectrum by the second spectrum; and
outputting a synthesized speech signal of the vocalized speech based on the modified spectrum.
7. The computer readable storage medium according to claim 6 , wherein the method further comprises detecting and processing motion of muscles around a mouth of the speaker when the sound signal is vocalized.