Result Details

The Language-Independent Bottleneck Features

VESELÝ, K.; KARAFIÁT, M.; GRÉZL, F.; JANDA, M.; EGOROVA, E. The Language-Independent Bottleneck Features. Proceedings of IEEE 2012 Workshop on Spoken Language Technology. Miami: IEEE Signal Processing Society, 2012. p. 336-341. ISBN: 978-1-4673-5124-9.
Type
conference paper
Language
English
Authors
Veselý Karel, Ing., Ph.D., DCGM (FIT)
Karafiát Martin, Ing., Ph.D., DCGM (FIT)
Grézl František, Ing., Ph.D., DCGM (FIT)
Janda Miloš, Ing., DCGM (FIT)
Egorova Ekaterina, Ing., Ph.D.
Abstract

The paper is about language-independent bottleneck features, which are generated by Multi-lingual Neural Network. This leads to features which are not biased towards any of the source languages, making the features effectively language independent.

Keywords

Language-Independent Bottleneck Features, Multilingual Neural Network

URL
Annotation

In this paper we present novel language-independent bottleneck (BN) feature extraction framework. In our experiments we have used Multilingual Artificial Neural Network (ANN), where each language is modelled by separate output layer, while all the hidden layers jointly model the variability of all the source languages. The key idea is that the entire
ANN is trained on all the languages simultaneously, thus the BN-features are not biased towards any of the languages. Exactly for this reason, the final BN-features are considered as language independent.

In the experiments with GlobalPhone database, we show that the Multilingual BN-features consistently outperform the Monolingual BN-features. Also, the cross-lingual generalisation is evaluated, where we train on 5 source languages and test on 3 other languages. The results show that the ANN can produce very good BN-features even for unseen languages. In some cases even better than if we would train the ANN on the target language only.

Published
2012
Pages
336–341
Proceedings
Proceedings of IEEE 2012 Workshop on Spoken Language Technology
Conference
IEEE 2012 Workshop on Spoken Language Technology
ISBN
978-1-4673-5124-9
Publisher
IEEE Signal Processing Society
Place
Miami
DOI
10.1109/SLT.2012.6424246
BibTeX 
@inproceedings{BUT97015,
  author="Karel {Veselý} and Martin {Karafiát} and František {Grézl} and Miloš {Janda} and Ekaterina {Egorova}",
  title="The Language-Independent Bottleneck Features",
  booktitle="Proceedings of IEEE 2012 Workshop on Spoken Language Technology",
  year="2012",
  pages="336--341",
  publisher="IEEE Signal Processing Society",
  address="Miami",
  doi="10.1109/SLT.2012.6424246",
  isbn="978-1-4673-5124-9",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2012/vesely_slt2012_0000336.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
Multilingual recognition and search in speech for electronic dictionaries, MPO, TIP, FR-TI1/034, start: 2009-09-01, end: 2013-08-31, completed
Speech recognition for low-resource languages, GACR, Postdoktorandské granty, GPP202/12/P604, start: 2012-01-01, end: 2014-12-31, completed
Technologies of speech processing for efficient human-machine communication, TAČR, Program aplikovaného výzkumu a experimentálního vývoje ALFA, TA01011328, start: 2011-01-01, end: 2014-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top