Result Details

Adapting Multilingual Neural Network Hierarchy to a New Language

GRÉZL, F.; KARAFIÁT, M. Adapting Multilingual Neural Network Hierarchy to a New Language. Proceedings of the 4th International Workshop on Spoken Language Technologies for Under- resourced Languages SLTU-2014. St. Petersburg, Russia, 2014. St. Petersburg: International Speech Communication Association, 2014. p. 39-45. ISBN: 978-5-8088-0908-6.
Type
conference paper
Language
English
Authors
Grézl František, Ing., Ph.D., DCGM (FIT)
Karafiát Martin, Ing., Ph.D., DCGM (FIT)
Abstract

This work addresses a thorough evaluation of multilingual techniquesfor adapting feature extraction neural network hierarchy -Stack Bottle-Neck system.

Keywords

feature extraction, Bottle-Neck features, neuralnetwork adaptation, multilingual neural networks, Stacked Bottle-Neck structure

URL
Annotation

The neural network based features became an inseparable part of state-of-the-art LVCSR systems. With the increasing accent on fast development of ASR system on limited resources, there is an effort to alleviate the need of large amount of transcribed in-domain data. One successful way is to use data from other languages. We present extensive evaluation of several strategies to adapt hierarchical neural network in search for the most effective one. To avoid the bias towards one target language, our strategies were evaluated on five languages. Also, several multilingual neural network hierarchies were trained on two sets of languages. Thus the results provide solid insight into the problem of adapting hierarchical system.

Published
2014
Pages
39–45
Proceedings
Proceedings of the 4th International Workshop on Spoken Language Technologies for Under- resourced Languages SLTU-2014. – St. Petersburg, Russia, 2014
Conference
The 4th International Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU'14)
ISBN
978-5-8088-0908-6
Publisher
International Speech Communication Association
Place
St. Petersburg
BibTeX 
@inproceedings{BUT111549,
  author="František {Grézl} and Martin {Karafiát}",
  title="Adapting Multilingual Neural Network Hierarchy to a New Language",
  booktitle="Proceedings of the 4th International Workshop on Spoken Language Technologies for Under- resourced Languages SLTU-2014. – St. Petersburg, Russia, 2014",
  year="2014",
  pages="39--45",
  publisher="International Speech Communication Association",
  address="St. Petersburg",
  isbn="978-5-8088-0908-6",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2014/grezl_sltu2014_multiling_adapt_p39_45.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
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
Speech recognition for low-resource languages, GACR, Postdoktorandské granty, GPP202/12/P604, start: 2012-01-01, end: 2014-12-31, completed
Zpracování, rozpoznávání a zobrazování multimediálních a 3D dat, BUT, Vnitřní projekty VUT, FIT-S-14-2506, start: 2014-01-01, end: 2016-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top