On the Investigation of Spectral Resolution Problem for Identification of Female Speakers in Bengali

Author

Patil, Hemant A. ; Dutta, P.K. ; Basu, T.K.

Author_Institution

Dr. B. C. Roy Eng. Coll., Durgapur

fYear

2006

fDate

15-17 Dec. 2006

Firstpage

375

Lastpage

380

Abstract

Voice biometrics is an economic method of person authentication with the help of machines because of low cost and high power computers. In this paper, we investigate the problem of spectral resolution in female speech for speaker identification. Finally, a speaker recognition system is presented to compare the relative performance of different LP-based features such as (LPC and LPCC) and filterbank-based features such as Mel-frequency cepstral coefficients (MFCC) for identification of female speakers. The results are shown for database collected from 15 female speakers in Bengali.

Keywords

biometrics (access control); channel bank filters; speaker recognition; Bengali; Mel-frequency cepstral coefficients; female speaker identification; filterbank-based features; linear prediction cepstral coefficients; person authentication; speaker recognition system; spectral resolution problem; voice biometrics; Authentication; Biometrics; Cepstral analysis; Costs; Linear predictive coding; Mel frequency cepstral coefficient; Power generation economics; Power system economics; Speaker recognition; Speech; Speaker recognition; feature extraction; polynomial classifier; spectral resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Technology, 2006. ICIT 2006. IEEE International Conference on

Conference_Location

Mumbai

Print_ISBN

1-4244-0726-5

Electronic_ISBN

1-4244-0726-5

Type

conf

DOI

10.1109/ICIT.2006.372386

Filename

4237708