Speaker Recognition The A TVS-UAM System at NIST SRE 05

Author

Gonzalez-Rodriguez, Joaquin ; Ramos-Castro, Daniel ; Toledano, Doroteo Torre ; Montero-Asenjo, Alberto ; Gonzalez-Dominguez, Javier ; Lopez-Moreno, Ignacio ; Fierrez-Aguilar, Julian ; Garcia-Romero, Daniel ; Ortega-Garcia, Javier

Author_Institution

Univ. Autonoma de Madrid

Volume

22

Issue

1

fYear

2007

Firstpage

15

Lastpage

21

Abstract

Automatic speaker recognition systems have been largely dominated by acoustic-spectral-based systems, relying in proper modelling of the short-term vocal tract of speakers. However, there is scientific and intuitive evidence that speaker-specific information is embedded in the speech signal in multiple short- and long-term characteristics. In this work, a multilevel speaker recognition system combining acoustic, phonotactic, and prosodic subsystems is presented and assessed by blind submission to NIST 2005 Speaker Recognition Evaluation

Keywords

speaker recognition; ATVS-UAM system; acoustic spectral based systems; automatic speaker recognition systems; short-term vocal tract; speaker-specific information; speech signal; HDTV; Information analysis; Loudspeakers; Mel frequency cepstral coefficient; NIST; Research and development; Security; Speaker recognition; Speech; Telephony;

fLanguage

English

Journal_Title

Aerospace and Electronic Systems Magazine, IEEE

Publisher

ieee

ISSN

0885-8985

Type

jour

DOI

10.1109/MAES.2007.327534

Filename

4126415