Detail publikace

Regularized Subspace n-Gram Model for Phonotactic iVector Extraction

SOUFIFAR, M. BURGET, L. PLCHOT, O. CUMANI, S. ČERNOCKÝ, J.

Originální název

Regularized Subspace n-Gram Model for Phonotactic iVector Extraction

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

This article describes an enhanced phonotactic iVector extraction model over the n-gram counts. In the first step, a subspace n-gram model is proposed to model conditional n-gram probabilities. Modeling different 3-gram histories with separated multinomial distributions shows promising results for the long condition however, we observed model over-fitting for the short duration conditions.

Klíčová slova

Language identification, Subspace modeling, Subspace multinomial model

Autoři

SOUFIFAR, M.; BURGET, L.; PLCHOT, O.; CUMANI, S.; ČERNOCKÝ, J.

Rok RIV

2013

Vydáno

25. 8. 2013

Nakladatel

International Speech Communication Association

Místo

Lyon

ISBN

978-1-62993-443-3

Kniha

Proceedings of Interspeech 2013

ISSN

2308-457X

Periodikum

Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).

Číslo

8

Stát

Francouzská republika

Strany od

74

Strany do

78

Strany počet

5

URL

BibTex

@inproceedings{BUT103567,
  author="Mehdi Mohammad {Soufifar} and Lukáš {Burget} and Oldřich {Plchot} and Sandro {Cumani} and Jan {Černocký}",
  title="Regularized Subspace n-Gram Model for Phonotactic iVector Extraction",
  booktitle="Proceedings of Interspeech 2013",
  year="2013",
  journal="Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).",
  number="8",
  pages="74--78",
  publisher="International Speech Communication Association",
  address="Lyon",
  isbn="978-1-62993-443-3",
  issn="2308-457X",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/soufifar_interspeech2013_IS131171.pdf"
}