Ing. Ondřej Glembek

Mikolov, T., Plchot, O., Glembek, O., Matějka, P., Burget, L., Černocký, J.: PCA-based Feature Extraction for Phonotactic Language Recognition, In: Proc. Odyssey 2010 - The Speaker and Language Recognition Workshop, Brno, CZ, ISCA, 2010, p. 251-255, ISBN 978-80-214-4114-9
Publication language:english
Original title:PCA-based Feature Extraction for Phonotactic Language Recognition
Title (cs):Extrakce parametrů pro fonotaktické rozpoznávání jazyka založená na PCA
Pages:251-255
Proceedings:Proc. Odyssey 2010 - The Speaker and Language Recognition Workshop
Conference:The Speaker and Language Recognition Workshop
Place:Brno, CZ
Year:2010
ISBN:978-80-214-4114-9
Publisher:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2010/mikolov_odys2010.pdf [PDF]
Keywords
speech, language recognition, automatic recognition, large amounts of data.
Annotation
This paper is on PCA-based Feature Extraction for Phonotactic Language Recognition. This technique improves speed of the training, in some cases more than 1000 times.
Abstract
Phonotactic language recognition is one of major techniques used for automatic recognition of spoken languages. We propose a feature extraction technique based on PCA to be used with SVM-based systems. This technique improves speed of the training, in some cases more than 1000 times, allowing systems to be effectively trained on much larger data sets. Speed-up of the test phase can be even greater, which makes the resulting systems much more useful for processing large amounts of data. We report our results on NIST LRE 2009 task.
BibTeX:
@INPROCEEDINGS{
   author = {Tomáš Mikolov and Oldřich Plchot and Ondřej Glembek and
	Pavel Matějka and Lukáš Burget and Jan Černocký},
   title = {PCA-based Feature Extraction for Phonotactic Language
	Recognition},
   pages = {251--255},
   booktitle = {Proc. Odyssey 2010 - The Speaker and Language Recognition
	Workshop},
   year = {2010},
   location = {Brno, CZ},
   publisher = {International Speech Communication Association},
   ISBN = {978-80-214-4114-9},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9317}
}

Your IPv4 address: 72.44.48.122
Switch to IPv6 connection

DNSSEC [dnssec]