| 摘要 |
PURPOSE:To obtain the voice recognition device whose accuracy of recognition can be confirmed by varying the loudness of an answer voice for confirming the recognition result of an input voice according to the value of a recognition score. CONSTITUTION:The input voice is recognized by a voice recognition part 11 and converted into a character string. This character string is supplied to a voice synthesis part 12 to synthesize a voice, which is amplified by an amplifier 13 and outputted. A gain setting part 14 sets the gain of the amplifier 13 according to the recognition score outputted from the recognition part 11. Namely, the gain of the amplifier 13 is adjusted by using the recognition score outputted by the recognition part 11 and 1st - 3rd values set in 1st - 3rd registers 15 - 17. |
