The research of feature extraction based on MFCC for speaker recognition

The feature extraction has proved to a primary issue of speaker recognition that represent the personality of the speaker from speech signals. In the paper, a new approach is presented for speaker recognition using the improved Mel frequency cepstral coefficients (MFCC). The experimental database consists of 30 speakers, 15 male and 15 female, collected in a sound proof room. The result of this experiment certificates that the improved Mel frequency cepstral coefficients derived parameters perform better than traditional Mel frequency cepstral coefficients based on hidden Markov models.