Detail publikace

Domain Adaptation Via Within-class Covariance Correction in I-Vector Based Speaker Recognition Systerms

GLEMBEK, O. MA, J. MATĚJKA, P. ZHANG, B. PLCHOT, O. BURGET, L. MATSOUKAS, S.

Originální název

Domain Adaptation Via Within-class Covariance Correction in I-Vector Based Speaker Recognition Systerms

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

speaker recognition, i-vectors, source normalization, LDA, inter-dataset variability compensation

Autoři

GLEMBEK, O.; MA, J.; MATĚJKA, P.; ZHANG, B.; PLCHOT, O.; BURGET, L.; MATSOUKAS, S.

Rok RIV

2014

Vydáno

4. 5. 2014

Nakladatel

IEEE Signal Processing Society

Místo

Florencie

ISBN

978-1-4799-2892-7

Kniha

Proceedings of ICASSP 2014

Strany od

4060

Strany do

4064

Strany počet

5

URL

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/"
}