I-vector based speaker recognition using advanced channel compensation techniques


Autoria(s): Kanagasundaram, Ahilan; Dean, David; Sridharan, Sridha; McLaren, Mitchell L.; Vogt, Robbie
Data(s)

04/01/2014

Resumo

This paper investigates advanced channel compensation techniques for the purpose of improving i-vector speaker verification performance in the presence of high intersession variability using the NIST 2008 and 2010 SRE corpora. The performance of four channel compensation techniques: (a) weighted maximum margin criterion (WMMC), (b) source-normalized WMMC (SN-WMMC), (c) weighted linear discriminant analysis (WLDA), and; (d) source-normalized WLDA (SN-WLDA) have been investigated. We show that, by extracting the discriminatory information between pairs of speakers as well as capturing the source variation information in the development i-vector space, the SN-WLDA based cosine similarity scoring (CSS) i-vector system is shown to provide over 20% improvement in EER for NIST 2008 interview and microphone verification and over 10% improvement in EER for NIST 2008 telephone verification, when compared to SN-LDA based CSS i-vector system. Further, score-level fusion techniques are analyzed to combine the best channel compensation approaches, to provide over 8% improvement in DCF over the best single approach, (SN-WLDA), for NIST 2008 interview/ telephone enrolment-verification condition. Finally, we demonstrate that the improvements found in the context of CSS also generalize to state-of-the-art GPLDA with up to 14% relative improvement in EER for NIST SRE 2010 interview and microphone verification and over 7% relative improvement in EER for NIST SRE 2010 telephone verification.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/59522/

Publicador

Elsevier

Relação

http://eprints.qut.edu.au/59522/4/59522.pdf

DOI:10.1016/j.csl.2013.04.002

Kanagasundaram, Ahilan, Dean, David, Sridharan, Sridha, McLaren, Mitchell L., & Vogt, Robbie (2014) I-vector based speaker recognition using advanced channel compensation techniques. Computer Speech and Language, 28(1), pp. 121-140.

Direitos

Copyright 2013 Elsevier

Fonte

School of Electrical Engineering & Computer Science; Information Security Institute; Science & Engineering Faculty

Palavras-Chave #Speaker verification #I-vector #GPLDA #LDA #SN-LDA #WLDA #SN-WLDA
Tipo

Journal Article