Doc. Dr. Ing. Jan Černocký

KARAFIÁT, M., BURGET, L., MATĚJKA, P., GLEMBEK, O. and ČERNOCKÝ, J.. iVector-Based Discriminative Adaptation for Automatic Speech Recognition. In: Proceedings of ASRU 2011. Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society, 2011, pp. 152-157. ISBN 978-1-4673-0366-8.
Publication language:english
Original title:iVector-Based Discriminative Adaptation for Automatic Speech Recognition
Title (cs):Diskriminativní adaptace pro automatické rozpoznávání řeči založená na i-vektorech
Pages:152-157
Proceedings:Proceedings of ASRU 2011
Conference:IEEE 2011 Workshop on Automatic Speech Recognition and Understanding
Place:Hilton Waikoloa Village, Big Island, Hawaii, US
Year:2011
ISBN:978-1-4673-0366-8
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/karafiat_asru2011_00152.pdf [PDF]
Keywords
Automatic speech recognition, I-vector, Discriminative adaptation
Annotation
The iVector is a low-dimensional fixed-length representation of information about speaker and acoustic environment. To utilize iVectors for adaptation, region dependent linear transforms (RDLT) are discriminatively trained using the MPE criterion on large amounts of annotated data to extract the relevant information from iVectors and to compensate speech features. The approach was tested on standard CTS data. We found it to be complementary to common adaptation techniques. On a well-tuned RDLT system with standard CMLLR adaptation we reached an 0.8% additive absolute WER improvement.
Abstract
This work describes a novel technique for discriminative feature-level adaptation for automatic speech recognition. The concept of iVectors popular in speaker recognition is used to extract information about a speaker or acoustic environment from a speech segment. The iVector is a low-dimensional fixed-length representation of such information. To utilize iVectors for adaptation, region dependent linear transforms (RDLT) are discriminatively trained using the MPE criterion on large amounts of annotated data to extract the relevant information from iVectors and to compensate speech features. The approach was tested on standard CTS data. We found it to be complementary to common adaptation techniques. On a well-tuned RDLT system with standard CMLLR adaptation we reached an 0.8% additive absolute WER improvement.
BibTeX:
@INPROCEEDINGS{
   author = {Martin Karafiát and Lukáš Burget and Pavel Matějka and
	Ondřej Glembek and Jan Černocký},
   title = {iVector-Based Discriminative Adaptation for Automatic Speech
	Recognition},
   pages = {152--157},
   booktitle = {Proceedings of ASRU 2011},
   year = {2011},
   location = {Hilton Waikoloa Village, Big Island, Hawaii, US},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4673-0366-8},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en?id=9762}
}

Your IPv4 address: 54.196.62.132
Switch to IPv6 connection

DNSSEC [dnssec]