Identity Feature Extraction Scheme of Curvelets for Speaker Recognition

Author

Jinfang, Wang ; Wang Jinbao ; Xiaojing, Zhao

Author_Institution

Commun. Eng. Coll., Jilin Univ., Changchun

fYear

2006

fDate

12-15 Dec. 2006

Firstpage

37

Lastpage

40

Abstract

This paper produces two types of the features of speaker recognition, mean of column elements (MC) and squared 2-norm of column elements (SNC). Both of them are derived from the curvelets representing the geometrical structure of squared modulus of Gabor representation of one-dimensional speech. The performance evaluation experiments have been conducted and the results indicate that with the score of 87.23%, the feature of mean of column elements bears a little better identification effect than that of squared 2-norm of column elements. The recognition accuracy of Mel-frequency cepstral coefficients (MFCC) reaches 86.52% based on the same speech database

Keywords

cepstral analysis; curvelet transforms; feature extraction; speaker recognition; Gabor representation squared modulus; Mel-frequency cepstral coefficients; curvelets; identity feature extraction scheme; mean of column elements; speaker recognition; squared 2-norm of column elements; Cepstral analysis; Educational institutions; Feature extraction; Mel frequency cepstral coefficient; Signal processing; Spatial databases; Speaker recognition; Speech recognition; Time frequency analysis; Visual databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Signal Processing and Communications, 2006. ISPACS '06. International Symposium on

Conference_Location

Yonago

Print_ISBN

0-7803-9732-0

Electronic_ISBN

0-7803-9733-9

Type

conf

DOI

10.1109/ISPACS.2006.364830

Filename

4212217