SOUND SIGNAL CORRECTING METHOD, SOUND SIGNAL CORRECTING APPARATUS AND RECORDING MEDIUM

摘要

PROBLEM TO BE SOLVED: To provide a sound signal correcting method, a sound signal correcting apparatus and a computer program that improve a speech recognition rate and does not generate an unnatural noise such as a watery noise by improving noise recognition precision for a sound signal including a noise and a speech acquired in an environment wherein a noise such as a stationary noise is generated.;SOLUTION: A sound signal correcting apparatus 1 converts an acquired sound signal into a phase spectrum and an amplitude spectrum by an FFT processing (Step S4), compares the amplitude spectrum of the obtained sound signal with a noise model so that a correction coefficient used for correcting the amplitude spectrum of the sound signal is derived (Step S5), smoothes waveform of the amplitude spectrum of the sound signal using the derived correction coefficient (Step S6), and converts the sound signal into a sound signal where the amplitude spectrum is corrected by performing an inverse FFT processing on the phase spectrum and the smoothed amplitude spectrum (Step S7).;COPYRIGHT: (C)2008,JPO&INPIT