Conference paper

GLEMBEK Ondřej, MATĚJKA Pavel, PLCHOT Oldřich, PEŠÁN Jan, BURGET Lukáš and SCHWARZ Petr. Migrating i-vectors Between Speaker Recognition Systems Using Regression Neural Networks. In: Proceedings of Interspeech 2015. Dresden: International Speech Communication Association, 2015, pp. 2327-2331. ISBN 978-1-5108-1790-6. ISSN 1990-9772.
Publication language:english
Original title:Migrating i-vectors Between Speaker Recognition Systems Using Regression Neural Networks
Title (cs):Převod i-vektorů mezi systémy pro rozpoznávání mluvčího pomocí regresních neuronových sítí
Pages:2327-2331
Proceedings:Proceedings of Interspeech 2015
Conference:INTERSPEECH 2015
Place:Dresden, DE
Year:2015
ISBN:978-1-5108-1790-6
Journal:Proceedings of Interspeech, Vol. 2015, No. 09, FR
ISSN:1990-9772
Publisher:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2015/glembek_interspeech2015_IS151314.pdf [PDF]
Files: 
+Type Name Title Size Last modified
iconglembek_interspeech2015_IS151314.pdf105 KB2017-03-01 18:32:52
^ Select all
With selected:
Keywords
speaker recognition, i-vector transformation, Regression Neural Networks, system migration
Annotation
We have shown that a linear transformation can be used to transform alien i-vectors to the reference i-vectors as the input to the reference PLDA system.
Abstract
This paper studies the scenario of migrating from one ivector- based speaker recognition system (SRE) to another, i.e. comparing the i-vectors produced by one system with those produced by another system. System migration would typically be motivated by deploying a system with improved recognition accuracy, e.g. because of technological upgrade, or because of the necessity of processing new kind of data, etc. Unfortunately, such migration is very likely to result in the incompatibility between the new and the original i-vectors and, therefore, in the inability of comparing the two. This work studies various topologies of Regression Neural Networks for transforming ivectors from three different systems so that-with slight loss in the accuracy-they are compatible with the reference system. We present the results on the NIST SRE 2010 telephone condition.
BibTeX:
@INPROCEEDINGS{
   author = {Ond{\v{r}}ej Glembek and Pavel Mat{\v{e}}jka and
	Old{\v{r}}ich Plchot and Jan Pe{\v{s}}{\'{a}}n and
	Luk{\'{a}}{\v{s}} Burget and Petr Schwarz},
   title = {Migrating i-vectors Between Speaker Recognition Systems
	Using Regression Neural Networks},
   pages = {2327--2331},
   booktitle = {Proceedings of Interspeech 2015},
   journal = {Proceedings of Interspeech},
   volume = {2015},
   number = {09},
   year = {2015},
   location = {Dresden, DE},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-5108-1790-6},
   ISSN = {1990-9772},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10968}
}

Your IPv4 address: 54.167.44.32
Switch to IPv6 connection

DNSSEC [dnssec]