摘要 |
PROBLEM TO BE SOLVED: To improve voice recognition performance by effectively use extraction of an acoustic feature amount with noise suppression, and extraction of an acoustic feature amount without noise suppression. SOLUTION: An acoustic analysis apparatus comprises: a determination section 15 for determining whether a background noise level is more than a prescribed level or not, based on a microphone input signal; a noise suppressing section 16 for suppressing a noise component included in the microphone input signal; an analyzing means for extracting the acoustic feature amount from the microphone input signal in which the noise component is suppressed by the noise suppressing section 16, or from the microphone input signal in which the noise component is not suppressed, according to the determination result by the determination section 15. COPYRIGHT: (C)2007,JPO&INPIT
|