Conference paper

BURGET Lukáš, PLCHOT Oldřich, CUMANI Sandro, GLEMBEK Ondřej, MATĚJKA Pavel and BRÜMMER Niko. Discriminatively Trained Probabilistic Linear Discriminant Analysis for Speaker Verification. In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011. Praha: IEEE Signal Processing Society, 2011, pp. 4832-4835. ISBN 978-1-4577-0537-3.
Publication language:english
Original title:Discriminatively Trained Probabilistic Linear Discriminant Analysis for Speaker Verification
Title (cs):Diskriminativně trénovaná pravděpodobnostní lineární diskriminační analýza pro ověřování mluvčího
Pages:4832-4835
Proceedings:Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Conference:International Conference on Acoustics, Speech and Signal Processing 2011
Place:Praha, CZ
Year:2011
ISBN:978-1-4577-0537-3
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/burget_icassp2011_4832.pdf [PDF]
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/burget_icassp2011_poster_discriminativePLDA.pdf [PDF]
Keywords
Speaker verification, Discriminative training, Probabilistic Linear Discriminant Analysis
Annotation
This paper is on Discriminatively Trained Probabilistic Linear Discriminant Analysis (PLDA) for Speaker Verification.
Abstract
Recently, i-vector extraction and Probabilistic Linear Discriminant Analysis (PLDA) have proven to provide state-of-the-art speaker verification performance. In this paper, the speaker verification score for a pair of i-vectors representing a trial is computed with a functional form derived from the successful PLDA generative model. In our case, however, parameters of this function are estimated based on a discriminative training criterion. We propose to use the objective function to directly address the task in speaker verification: discrimination between same-speaker and different-speaker trials. Compared with a baseline which uses a generatively trained PLDA model, discriminative training provides up to 40% relative improvement on the NIST SRE 2010 evaluation task.
BibTeX:
@INPROCEEDINGS{
   author = {Luk{\'{a}}{\v{s}} Burget and Old{\v{r}}ich Plchot and Sandro
	Cumani and Ond{\v{r}}ej Glembek and Pavel Mat{\v{e}}jka and
	Niko Br{\"{u}}mmer},
   title = {Discriminatively Trained Probabilistic Linear Discriminant
	Analysis for Speaker Verification},
   pages = {4832--4835},
   booktitle = {Proceedings of the 2011 IEEE International Conference on
	Acoustics, Speech, and Signal Processing, ICASSP 2011},
   year = {2011},
   location = {Praha, CZ},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4577-0537-3},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9653}
}

Your IPv4 address: 54.158.152.80
Switch to IPv6 connection

DNSSEC [dnssec]