Result Details

Multilingual Bottleneck Features for Language Recognition

FÉR, R.; MATĚJKA, P.; GRÉZL, F.; PLCHOT, O.; ČERNOCKÝ, J. Multilingual Bottleneck Features for Language Recognition. In Proceedings of Interspeech 2015. Proceedings of Interspeech. Dresden: International Speech Communication Association, 2015. no. 09, p. 389-393. ISBN: 978-1-5108-1790-6. ISSN: 1990-9772.
Type
conference paper
Language
English
Authors
Fér Radek, Ing., DCGM (FIT)
Matějka Pavel, Ing., Ph.D., DCGM (FIT)
Grézl František, Ing., Ph.D., DCGM (FIT)
Plchot Oldřich, Ing., Ph.D., DCGM (FIT)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Abstract

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

Keywords

multilingual training, stacked bottleneck features,language identification

URL
Annotation

In this paper, we investigate Multilingual Stacked Bottleneck Features (SBN) in language recognition domain. These features are extracted using bottleneck neural networks trained on data from multiple languages. Previous results have shown benefits of multilingual training of SBN feature extractor for speech recognition. Here we focus on its impact on language recognition. We present results obtained with monolingual and multilingual networks, and their fusions. Using multilingual features, we obtain 16% relative improvement on 3 s condition of NIST LRE09 dataset with respect to features trained on a single language

Published
2015
Pages
389–393
Journal
Proceedings of Interspeech, vol. 2015, no. 09, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2015
Conference
Interspeech Conference
ISBN
978-1-5108-1790-6
Publisher
International Speech Communication Association
Place
Dresden
UT WoS
000380581600079
EID Scopus
2-s2.0-84959125057
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",
  booktitle="Proceedings of Interspeech 2015",
  year="2015",
  journal="Proceedings of Interspeech",
  volume="2015",
  number="09",
  pages="389--393",
  publisher="International Speech Communication Association",
  address="Dresden",
  isbn="978-1-5108-1790-6",
  issn="1990-9772",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2015/fer_interspeech2015_IS150860.pdf"
}
Projects
Centrum excelence IT4Innovations, MŠMT, Operační program Výzkum a vývoj pro inovace, ED1.1.00/02.0070, start: 2011-01-01, end: 2015-12-31, completed
DARPA Robust Automatic Transcription of Speech (RATS) - RATS Patrol II, BBN, start: 2015-02-23, end: 2017-03-31, completed
Enabling automatic speaker verification to broad spectrum of users in the security domain, MV, Program bezpečnostního výzkumu České republiky 2010 - 2015, VG20132015129, start: 2013-04-01, end: 2015-09-30, completed
IARPA Building Speech Recognition for Keyword Search in a New Language in a Week with Limited Training Data (BABEL) - Babelon, BBN, start: 2012-03-05, end: 2016-11-04, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top