Publication detail

Multilingual Bottleneck Features for Language Recognition

FÉR, R. MATĚJKA, P. GRÉZL, F. PLCHOT, O. ČERNOCKÝ, J.

Original Title

Multilingual Bottleneck Features for Language Recognition

English Title

Multilingual Bottleneck Features for Language Recognition

Type

conference paper

Language

en

Original Abstract

In this work, we applied multilingual training paradigm of SBN neural networks to extract linguistically rich features.

English abstract

In this work, we applied multilingual training paradigm of SBN neural networks to extract linguistically rich features.

Keywords

multilingual training, stacked bottleneck features, language identification

RIV year

2015

Released

06.09.2015

Publisher

International Speech Communication Association

Location

Dresden

ISBN

978-1-5108-1790-6

Book

Proceedings of Interspeech 2015

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

389

Pages to

393

Pages count

5

URL

Documents

BibTex


@inproceedings{BUT119902,
  author="Radek {Fér} and Pavel {Matějka} and František {Grézl} and Oldřich {Plchot} and Jan {Černocký}",
  title="Multilingual Bottleneck Features for Language Recognition",
  annote="In this work, we applied multilingual training paradigm of SBN neural networks to
extract linguistically rich features.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2015",
  chapter="119902",
  edition="NEUVEDEN",
  howpublished="electronic, physical medium",
  institution="International Speech Communication Association",
  number="09",
  year="2015",
  month="september",
  pages="389--393",
  publisher="International Speech Communication Association",
  type="conference paper"
}