Detail publikace

Language Recognition in iVectors Space

MARTÍNEZ GONZÁLEZ, D. PLCHOT, O. BURGET, L. GLEMBEK, O. MATĚJKA, P.

Originální název

Language Recognition in iVectors Space

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

We have introduced a novel approach for language recognition.Three classifiers (linear generative model, SVM and logistic regression)have been tested in the iVector space, and all outperformthe state-of-the-art JFA system. Very simple and fast classifierbased on linear generative model provides excellent performanceover all conditions. The advantage of this classifieris also its scalability: addition of a new language only requiresestimating the mean over the corresponding iVectors. Most ofthe computational load is in the iVector generation. Hence, as anext step, we will try to obtain iVectors from the utterances andthe corresponding sufficient statistics in a more direct way.

Klíčová slova

Acoustic Language Recognition, iVectors, JointFactor Analysis

Autoři

MARTÍNEZ GONZÁLEZ, D.; PLCHOT, O.; BURGET, L.; GLEMBEK, O.; MATĚJKA, P.

Rok RIV

2011

Vydáno

27. 8. 2011

Nakladatel

International Speech Communication Association

Místo

Florence

ISBN

978-1-61839-270-1

Kniha

Proceedings of Interspeech 2011

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2011

Číslo

8

Stát

Francouzská republika

Strany od

861

Strany do

864

Strany počet

4

URL

BibTex

@inproceedings{BUT76437,
  author="David {Martínez González} and Oldřich {Plchot} and Lukáš {Burget} and Ondřej {Glembek} and Pavel {Matějka}",
  title="Language Recognition in iVectors Space",
  booktitle="Proceedings of Interspeech 2011",
  year="2011",
  journal="Proceedings of Interspeech",
  volume="2011",
  number="8",
  pages="861--864",
  publisher="International Speech Communication Association",
  address="Florence",
  isbn="978-1-61839-270-1",
  issn="1990-9772",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/martinez_interspeech2011_291.pdf"
}