Přístupnostní navigace
E-application
Search Search Close
Publication detail
GLEMBEK, O. MA, J. MATĚJKA, P. ZHANG, B. PLCHOT, O. BURGET, L. MATSOUKAS, S.
Original Title
Domain Adaptation Via Within-class Covariance Correction in I-Vector Based Speaker Recognition Systerms
Type
conference paper
Language
English
Original Abstract
In this paper, we have shown a technique of within-class correction for Linear Discriminant Analysis estimation. We have shown that when correct dataset clustering is used, adapting the within-class covariance of LDA by low-rank between-dataset covariance matrix can lead to significant improvement of the system, namely up to 70% in the Domain Adaptation Task, and 17.5% and 36% relative in the RATS unmatched and semi-matched tasks, respectively. The dataset clustering problem gave us an interesting direction for future research.
Keywords
speaker recognition, i-vectors, source normalization, LDA, inter-dataset variability compensation
Authors
GLEMBEK, O.; MA, J.; MATĚJKA, P.; ZHANG, B.; PLCHOT, O.; BURGET, L.; MATSOUKAS, S.
RIV year
2014
Released
4. 5. 2014
Publisher
IEEE Signal Processing Society
Location
Florencie
ISBN
978-1-4799-2892-7
Book
Proceedings of ICASSP 2014
Pages from
4060
Pages to
4064
Pages count
5
URL
https://www.fit.vut.cz/research/publication/10555/
BibTex
@inproceedings{BUT111543, author="Ondřej {Glembek} and Jeff {Ma} and Pavel {Matějka} and Bing {Zhang} and Oldřich {Plchot} and Lukáš {Burget} and Spyros {Matsoukas}", title="Domain Adaptation Via Within-class Covariance Correction in I-Vector Based Speaker Recognition Systerms", booktitle="Proceedings of ICASSP 2014", year="2014", pages="4060--4064", publisher="IEEE Signal Processing Society", address="Florencie", doi="10.1109/ICASSP.2014.6854359", isbn="978-1-4799-2892-7", url="https://www.fit.vut.cz/research/publication/10555/" }