Speaker identification in mismatch training and testing conditions

Author

Alonso-Martínez, Carlos ; Faundez-Zanuy, Marcos

Author_Institution

Univ. Politecnica de Catalunya, Barcelona, Spain

Volume

2

fYear

2000

fDate

2000

Abstract

This paper presents an exhaustive study about the robustness of several parameterizations, with a new database specially acquired for the purpose of this study. This database includes the following variations: different recording sessions (including telephonic and microphonic recordings), recording rooms, and languages (it has been obtained from a bilingual set of speakers). This study has been performed with two identification algorithms (vector quantization and covariance matrices) and reveals that the combination of several parameterizations can improve the robustness in all the scenarios

Keywords

cepstral analysis; covariance matrices; speaker recognition; vector quantisation; bilingual speakers; covariance matrices; identification algorithms; languages; microphonic recording; mismatch training; parameterizations; recording rooms; recording sessions; robustness; speaker identification; telephonic recording; testing conditions; vector quantization; CD recording; Databases; ISDN; Microphones; Natural languages; Robustness; Speaker recognition; Speech; Testing; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on

Conference_Location

Istanbul

ISSN

1520-6149

Print_ISBN

0-7803-6293-4

Type

conf

DOI

10.1109/ICASSP.2000.859176

Filename

859176