Článek ve sborníku konference

 
Glembek, O., Burget, L., Kenny, P., Karafiát, M., Matějka, P.: Simplification and optimization of I-Vector Extraction, In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Praha, CZ, IEEESP, 2011, s. 4516-4519, ISBN 978-1-4577-0537-3
Jazyk publikace:angličtina
Název publikace:Simplification and optimization of I-Vector Extraction
Název (cs):Zjednodušení a optimalisace extrakce i-vektorů
Strany:4516-4519
Sborník:Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Konference:International Conference on Acoustics, Speech and Signal Processing 2011
Místo vydání:Praha, CZ
Rok:2011
ISBN:978-1-4577-0537-3
Vydavatel:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/glembek_icassp2011_4516.pdf [PDF]
Klíčová slova
speaker recognition, i-vectors, Joint Factor Analysis, PCA, HLDA
Anotace
Publikace pojednává o zjednodušení a optimalisaci extrakce i-vektorů. Autorům se podařilo zredukovat požadavky na paměť a dobu zpracování při trénování extrakce i-vektorů.
Abstrakt
This paper introduces some simplifications to the i-vector speaker recognition systems. I-vector extraction as well as training of the i-vector extractor can be an expensive task both in terms of memory and speed. Under certain assumptions, the formulas for i-vector extraction-also used in i-vector extractor training-can be simplified and lead to a faster and memory more efficient code. The first assumption is that the GMM component alignment is constant across utterances and is given by the UBM GMM weights. The second assumption is that the i-vector extractor matrix can be linearly transformed so that its per-Gaussian components are orthogonal. We use PCA and HLDA to estimate this transform.
BibTeX:
@INPROCEEDINGS{
   author = {Ondřej Glembek and Lukáš Burget and Patrick Kenny and Martin
	Karafiát and Pavel Matějka},
   title = {Simplification and optimization of I-Vector Extraction},
   pages = {4516--4519},
   booktitle = {Proceedings of the 2011 IEEE International Conference on
	Acoustics, Speech, and Signal Processing, ICASSP 2011},
   year = {2011},
   location = {Praha, CZ},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4577-0537-3},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9655}
}