Detail publikace

Domain adaptation via within-class covariance correction in I-vector based speaker recognition systems

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 systems

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In this paper, we have shown a technique of within-class correctionfor Linear Discriminant Analysis estimation. We have shown thatwhen correct dataset clustering is used, adapting the within-classcovariance of LDA by low-rank between-dataset covariance matrixcan lead to significant improvement of the system, namely up to70% in the Domain Adaptation Task, and 17.5% and 36% relativein the RATS unmatched and semi-matched tasks, respectively. Thedataset clustering problem gave us an interesting direction for futureresearch.

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

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 systems",
  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/"
}

Dokumenty

glembek_icassp2014_p4060.pdf