Speech recognition apparatus for AV equipment

A speech recognition apparatus used for AV equipment and operable for outputting multichannel sound through a plurality of loudspeakers, recognizing a user's speech inputted through a microphone, and causing the AV equipment to perform a predetermined process, said apparatus comprising:

• a monaural conversion part for converting multichannel signals transmitted to the plurality of loudspeakers into a monaural signal;
• a single echo canceller, provided with an output from the microphone (microphone output) and an output from said monaural conversion part (monaural output), for estimating echo sound of the multichannel sound based on the monaural signal and eliminating the echo sound from the microphone output;
• a speech recognition part for recognizing the user's speech based on an output from said single echo canceller (echo canceller output);
• a switching part for switching between the multichannel signals and the monaural signal transmitted to the plurality of loudspeakers;
• a start instruction part for providing an instruction to start speech recognition operation;
• an end instruction part for providing an instruction to end the speech recognition operation;
• and
• a state setting part for setting, responsive to the instructions from said start instruction part and said end instruction part, said speech recognition part to an active state or wait state;
• wherein said switching part:
• inputs the multichannel signals to the plurality of loudspeakers when said state setting part sets said speech recognition part to the wait state;
• and
• inputs the monaural signal to the plurality of loudspeakers when said state setting part sets said speech recognition part to the active state.