Eigenvoice modeling for cross likelihood ratio based speaker clustering : a Bayesian approach


Autoria(s): Wang, David; Vogt, Robert J.; Sridharan, Sridha
Data(s)

01/06/2013

Resumo

This paper proposes the use of Bayesian approaches with the cross likelihood ratio (CLR) as a criterion for speaker clustering within a speaker diarization system, using eigenvoice modeling techniques. The CLR has previously been shown to be an effective decision criterion for speaker clustering using Gaussian mixture models. Recently, eigenvoice modeling has become an increasingly popular technique, due to its ability to adequately represent a speaker based on sparse training data, as well as to provide an improved capture of differences in speaker characteristics. The integration of eigenvoice modeling into the CLR framework to capitalize on the advantage of both techniques has also been shown to be beneficial for the speaker clustering task. Building on that success, this paper proposes the use of Bayesian methods to compute the conditional probabilities in computing the CLR, thus effectively combining the eigenvoice-CLR framework with the advantages of a Bayesian approach to the diarization problem. Results obtained on the 2002 Rich Transcription (RT-02) Evaluation dataset show an improved clustering performance, resulting in a 33.5% relative improvement in the overall Diarization Error Rate (DER) compared to the baseline system.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/56402/

Publicador

Elsevier Ltd.

Relação

http://eprints.qut.edu.au/56402/1/CSL.pdf

DOI:10.1016/j.csl.2012.12.001

Wang, David, Vogt, Robert J., & Sridharan, Sridha (2013) Eigenvoice modeling for cross likelihood ratio based speaker clustering : a Bayesian approach. Computer Speech and Language, 27(4), pp. 1011-1027.

http://purl.org/au-research/grants/ARC/LP0991238

Direitos

Copyright 2012 Elsevier Ltd.

This is the author’s version of a work that was accepted for publication in Computer Speech and Language. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Computer Speech and Language, [VOL 27, ISSUE 4, (2013)] DOI: 10.1016/j.csl.2012.12.001

Fonte

Faculty of Built Environment and Engineering; Information Security Institute

Palavras-Chave #090609 Signal Processing #eigenvoice modeling #joint factor analysis #cross likelihood ratio #speaker clustering #speaker diarization
Tipo

Journal Article