Conference paper

GLEMBEK Ondřej, BURGET Lukáš, BRÜMMER Niko, PLCHOT Oldřich and MATĚJKA Pavel. Discriminatively Trained i-vector Extractor for Speaker Verification. In: Proceedings of Interspeech 2011. Florence: International Speech Communication Association, 2011, pp. 137-140. ISBN 978-1-61839-270-1. ISSN 1990-9772.
Publication language:english
Original title:Discriminatively Trained i-vector Extractor for Speaker Verification
Title (cs):Diskriminativně trénovaný extraktor i-vektorů pro ověřování mluvčího
Pages:137-140
Proceedings:Proceedings of Interspeech 2011
Conference:Interspeech 2011
Place:Florence, IT
Year:2011
ISBN:978-1-61839-270-1
Journal:Proceedings of Interspeech, Vol. 2011, No. 8, FR
ISSN:1990-9772
Publisher:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/glembek_interspeech2011_386.pdf [PDF]
Keywords
speaker verification, i-vectors, PLDA, discriminative training
Annotation
We have proposed a technique for discriminative training of the i-vector extractor parameters using cross-entropy as the error function. We have applied the technique both to the original i-vector extractor and to its simplified version. In both cases, the discriminative training was effective, giving higher relative improvement in the simplified case.
Abstract
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.
BibTeX:
@INPROCEEDINGS{
   author = {Ond{\v{r}}ej Glembek and Luk{\'{a}}{\v{s}} Burget and Niko
	Br{\"{u}}mmer and Old{\v{r}}ich Plchot and Pavel
	Mat{\v{e}}jka},
   title = {Discriminatively Trained i-vector Extractor for Speaker
	Verification},
   pages = {137--140},
   booktitle = {Proceedings of Interspeech 2011},
   journal = {Proceedings of Interspeech},
   volume = {2011},
   number = {8},
   year = {2011},
   location = {Florence, IT},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-61839-270-1},
   ISSN = {1990-9772},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9752}
}

Your IPv4 address: 54.198.31.213
Switch to IPv6 connection

DNSSEC [dnssec]