Speaker feature extraction from pitch information based on spectral subtraction for speaker identification

Robust speaker feature extraction under noise conditions is an important issue for application of a speaker recognition system. It is well known that LPC cepstrum, which expresses the spectral envelope, is e ective for speaker recognition. This implies that the spectral rough structure is e ective for speaker recognition. However, LPC cepstrum is a noise-sensitive feature. On the other hand, spectral subtraction is an effective speech enhancement method under stationary noise conditions. In this study, we developed a new method for feature extraction based on spectral subtraction and noise robust spectral rough structures, and we evaluated the e ectiveness of the feature extraction method in speaker identi cation experiments.