| 摘要 |
PROBLEM TO BE SOLVED: To prevent voices from being recognized erroneously. SOLUTION: In a starting sound detecting part 46, a starting sound (for example, a sound which is generated by clapping both hands) being a sound whose power is equal to or larger than a threshold L and a sound which does not continue for a time equal to or longer than a threshold T1 is detected, and in a feature parameter extracting part 41 and a matching part 42, voice recognition is performed in accordance with the detecting of the starting sound.
|
