Conference paper

LEI Yun, BURGET Lukáš and SCHEFFER Nicolas. A Noise Robust I-Vector Extractor Using Vector Taylor Series For Speaker Recognition. In: Proceedings of ICASSP 2013. Vancouver: IEEE Signal Processing Society, 2013, pp. 6788-6791. ISBN 978-1-4799-0355-9. Available from: http://www.fit.vutbr.cz/research/groups/speech/publi/2013/lei_icassp2013_0006788.pdf
Publication language:english
Original title:A Noise Robust I-Vector Extractor Using Vector Taylor Series For Speaker Recognition
Title (cs):Extraktor I-vektorů využívající vektorovou Taylorovu řadu pro rozpoznávání mluvčího odolné vůči šumu
Pages:6788-6791
Proceedings:Proceedings of ICASSP 2013
Conference:38th International Conference on Acoustics, Speech, and Signal Processing
Place:Vancouver, CA
Year:2013
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2013/lei_icassp2013_0006788.pdf
ISBN:978-1-4799-0355-9
Publisher:IEEE Signal Processing Society
Keywords
speaker recognition, Vector Taylor Series, ivector, noisy speaker verification, noise compensation
Annotation
This article describes a successfull adapation of the VTS approach to speaker recognition by proposing a new i-vector extraction framework.
Abstract
We propose a novel approach for noise-robust speaker recognition, where the model of distortions caused by additive and convolutive noises is integrated into the i-vector extraction framework. The model is based on a vector taylor series (VTS) approximation widely successful in noise robust speech recognition. The model allows for extracting "cleaned-up" i-vectors which can be used in a standard i-vector back end. We evaluate the proposed framework on the PRISM corpus, a NIST-SRE like corpus, where noisy conditions were created by artificially adding babble noises to clean speech segments. Results show that using VTS i-vectors present significant improvements in all noisy conditions compared to a state-of-theart baseline speaker recognition. More importantly, the proposed framework is robust to noise, as improvements are maintained when the system is trained on clean data.
BibTeX:
@INPROCEEDINGS{
   author = {Yun Lei and Luk{\'{a}}{\v{s}} Burget and Nicolas Scheffer},
   title = {A Noise Robust I-Vector Extractor Using Vector Taylor Series
	For Speaker Recognition},
   pages = {6788--6791},
   booktitle = {Proceedings of ICASSP 2013},
   year = {2013},
   location = {Vancouver, CA},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4799-0355-9},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10338}
}

Your IPv4 address: 23.20.48.226
Switch to IPv6 connection

DNSSEC [dnssec]