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

Anglický název

Regularized Subspace n-Gram Model for Phonotactic iVector Extraction

Jazyk

en

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.

Anglický 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.

Dokumenty

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",
  annote="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.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2013",
  chapter="103567",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  number="8",
  year="2013",
  month="august",
  pages="74--78",
  publisher="International Speech Communication Association",
  type="conference paper"
}