Phonetic speaker recognition

Author

Kohler, Mary A. ; Andrews, Walter D. ; Campbell, Joseph P. ; Herndndez-Cordero, J.

Author_Institution

Dept. of Defense, MIT, Lexington, MA, USA

Volume

2

fYear

2001

fDate

4-7 Nov. 2001

Firstpage

1557

Abstract

This paper introduces a novel language-independent speaker-recognition system based on differences in dynamic realization of phonetic features (i.e., pronunciation) between speakers rather than spectral differences in voice quality. The system exploits phonetic information from six languages to perform text independent speaker recognition. All experiments were performed on the NIST 2001 Speaker Recognition Evaluation Extended Data Task. Recognition results are provided for unigram, bigram, and trigram models. Performance for each of the three models is examined for phones from each individual language and the final multilanguage fused system. Additional fusion experiments demonstrate that speaker recognition capability is maintained even without phonetic information in the language of the speaker.

Keywords

feature extraction; speaker recognition; speech processing; NIST 2001 Speaker Recognition Evaluation Extended Data Task; bigram model; dynamic realization; language-independent speaker recognition; multilanguage fused system; performance; phonetic features; phonetic speaker recognition; pronunciation; refracted phone sequences; text independent speaker recognition; trigram model; unigram model; Acoustic testing; Automatic speech recognition; Cepstral analysis; Echo cancellers; NIST; Natural languages; Performance evaluation; Speaker recognition; Speech processing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2001. Conference Record of the Thirty-Fifth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-7803-7147-X

Type

conf

DOI

10.1109/ACSSC.2001.987748

Filename

987748