Result Details

Discriminatively Trained i-vector Extractor for Speaker Verification

GLEMBEK, O.; BURGET, L.; BRÜMMER, N.; PLCHOT, O.; MATĚJKA, P. Discriminatively Trained i-vector Extractor for Speaker Verification. In Proceedings of Interspeech 2011. Proceedings of Interspeech. Florence: International Speech Communication Association, 2011. no. 8, p. 137-140. ISBN: 978-1-61839-270-1. ISSN: 1990-9772.
Type
conference paper
Language
English
Authors
Glembek Ondřej, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Brümmer Niko
Plchot Oldřich, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Matějka Pavel, Ing., Ph.D., DCGM (FIT)
Abstract

We have proposed a technique for discriminative training of thei-vector extractor parameters using cross-entropy as the errorfunction. We have applied the technique both to the originali-vector extractor and to its simplified version. In both cases,the discriminative training was effective, giving higher relativeimprovement in the simplified case.

Keywords

speaker verification, i-vectors, PLDA, discriminativetraining

URL
Annotation

We propose a strategy for discriminative training of the ivector extractor in speaker recognition. The original i-vector extractor training was based on the maximum-likelihood generative modeling, where the EM algorithm was used. In our approach, the i-vector extractor parameters are numerically optimized to minimize the discriminative cross-entropy error function. Two versions of the i-vector extraction are studied-the original approach as defined for Joint Factor Analysis, and the simplified version, where orthogonalization of the i-vector extractor matrix is performed.

Published
2011
Pages
137–140
Journal
Proceedings of Interspeech, vol. 2011, no. 8, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2011
Conference
Interspeech Conference
ISBN
978-1-61839-270-1
Publisher
International Speech Communication Association
Place
Florence
EID Scopus
2-s2.0-84865767579
BibTeX 
@inproceedings{BUT76447,
  author="Ondřej {Glembek} and Lukáš {Burget} and Niko {Brümmer} and Oldřich {Plchot} and Pavel {Matějka}",
  title="Discriminatively Trained i-vector Extractor for Speaker Verification",
  booktitle="Proceedings of Interspeech 2011",
  year="2011",
  journal="Proceedings of Interspeech",
  volume="2011",
  number="8",
  pages="137--140",
  publisher="International Speech Communication Association",
  address="Florence",
  isbn="978-1-61839-270-1",
  issn="1990-9772",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/glembek_interspeech2011_386.pdf"
}
Projects
IARPA Biometrics Exploitation Science and Technology (BEST) - Promoting Robustness in Speaker Modeling (PRISM), IARPA, start: 2009-12-07, end: 2011-12-30, completed
Security-Oriented Research in Information Technology, MŠMT, Institucionální prostředky SR ČR (např. VZ, VC), MSM0021630528, start: 2007-01-01, end: 2013-12-31, running
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top