Faculty of Information Technology, BUT

Publication Details

Simplification and optimization of I-Vector Extraction

GLEMBEK Ondřej, BURGET Lukáš, KENNY Patrick, KARAFIÁT Martin and MATĚJKA Pavel. Simplification and optimization of I-Vector Extraction. In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011. Praha: IEEE Signal Processing Society, 2011, pp. 4516-4519. ISBN 978-1-4577-0537-3.
Czech title
Zjednodušení a optimalisace extrakce i-vektorů
Type
conference paper
Language
english
Authors
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Kenny Patrick (CRIM)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords
speaker recognition, i-vectors, Joint Factor Analysis, PCA, HLDA
Abstract
We managed to reduce the memory requirements and processing time for the i-vector extractor training so that higher dimensions can be now used while retaining the recognition accuracy. As for i-vector extraction, we managed to reduce the complexity of the algorithm with sacrificing little recognition accuracy, which makes this technique usable in small-scale devices.
Annotation
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.
Published
2011
Pages
4516-4519
Proceedings
Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Conference
International Conference on Acoustics, Speech and Signal Processing 2011, Praha, CZ
ISBN
978-1-4577-0537-3
Publisher
IEEE Signal Processing Society
Place
Praha, CZ
BibTeX
@INPROCEEDINGS{FITPUB9655,
   author = "Ond\v{r}ej Glembek and Luk\'{a}\v{s} Burget and Patrick Kenny and Martin Karafi\'{a}t and Pavel Mat\v{e}jka",
   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 = "https://www.fit.vut.cz/research/publication/9655"
}
Back to top