Complementary Features for Speaker Verification Based on Genetic Algorithms

Author

Charbuillet, C. ; Gas, B. ; Chetouani, Mohamed ; Zarader, J.L.

Author_Institution

Groupe Perception et Reseaux Connexionnistes, Univ. Pierre et Marie Curie-Paris, France

Volume

4

fYear

2007

fDate

15-20 April 2007

Abstract

Speech recognition systems usually need a feature extraction stage aiming at obtaining the best signal representation. State of the art speaker verification systems are based on cepstrals features like MFCC, LFCC or LPCC. In this article, we propose to use a genetic algorithm to provide new features able to complete the LFCC´s. We present an adaptation of the common LFCC feature extractor which consists in designing a filter bank, optimized for a high level fusion issue. Experiments are carried out using a state of the art speaker verification system. Results show that the proposed method improves the system performances on the 2006 Nist SRE Database.

Keywords

channel bank filters; feature extraction; genetic algorithms; speaker recognition; speech processing; complementary features; feature extraction; filter bank; genetic algorithms; speaker verification; speech recognition systems; Cepstral analysis; Design optimization; Feature extraction; Filter bank; Genetic algorithms; Mel frequency cepstral coefficient; NIST; Signal representations; Spatial databases; Speech recognition; Feature extraction; Genetic algorithms; Speaker recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on

Conference_Location

Honolulu, HI

ISSN

1520-6149

Print_ISBN

1-4244-0727-3

Type

conf

DOI

10.1109/ICASSP.2007.366905

Filename

4218093