Detail publikace

iVector Approach to Phonotactic Language Recognition

Originální název

iVector Approach to Phonotactic Language Recognition

Anglický název

iVector Approach to Phonotactic Language Recognition

Jazyk

en

Originální abstrakt

We proposed a novel method to extract the iVectors by means of subspace multinomial modelling of the n-gram counts. Using the proposed subspace model, the huge vector of the n-gram counts are represented by the low-dimensional iVector while preserving the discriminative power of the vector.

Anglický abstrakt

We proposed a novel method to extract the iVectors by means of subspace multinomial modelling of the n-gram counts. Using the proposed subspace model, the huge vector of the n-gram counts are represented by the low-dimensional iVector while preserving the discriminative power of the vector.

BibTex


@inproceedings{BUT76439,
  author="Mehdi Mohammad {Soufifar} and Marcel {Kockmann} and Lukáš {Burget} and Oldřich {Plchot} and Ondřej {Glembek} and Torbjorn {Svendsen}",
  title="iVector Approach to Phonotactic Language Recognition",
  annote="We proposed a novel method to extract the iVectors by means of subspace
multinomial modelling of the n-gram counts. Using the proposed subspace model,
the huge vector of the n-gram counts are represented by the low-dimensional
iVector while preserving the discriminative power of the vector.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2011",
  chapter="76439",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  number="8",
  year="2011",
  month="august",
  pages="2913--2916",
  publisher="International Speech Communication Association",
  type="conference paper"
}