The research of feature extraction based on MFCC for speaker recognition

Author

Zhang Wanli ; Li Guoxin

Author_Institution

Electron. Inf. & Eng., Changchun Univ., Changchun, China

fYear

2013

fDate

12-13 Oct. 2013

Firstpage

1074

Lastpage

1077

Abstract

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.

Keywords

feature extraction; hidden Markov models; speaker recognition; MFCC; Mel frequency cepstral coefficients; feature extraction; hidden Markov models; sound proof room; speaker personality representation; speaker recognition; Feature extraction; Mel frequency cepstral coefficient; Speaker recognition; Speech; Speech processing; Speech recognition; Testing; Mel frequency cepstral coefficients; feature extraction; speaker recognition; weighted Mel frequency cepstral coefficients;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Network Technology (ICCSNT), 2013 3rd International Conference on

Conference_Location

Dalian

Type

conf

DOI

10.1109/ICCSNT.2013.6967289

Filename

6967289