关键词: 语音识别, 小波调制尺度, 语音特征

Abstract: Based on time-frequency analysis, the theory of estimating a modulation scale representation was discussed, and a new method of features extraction for speech recognition was proposed. Considering specialty of human auditory perception and disturbances, wavelet analysis was used instead of Fourier analysis for modulation frequency transform, and wavelet modulation scales was acquired as speech features for recognition. For further attenuating the effects of disturbances, subband normalization was introduced with the wavelet modulation scales. Experiments for the Chinese syllables recognition show extracting the wavelet modulation scales as the dynamic features outperform the frequency differences both in noise environments and in time misalignment cases.

Key words: speech recognition, wavelet modulation scale, speech features