Result Details

Hierarchical Neural Net Architectures for Feature Extraction in ASR

GRÉZL, F.; KARAFIÁT, M. Hierarchical Neural Net Architectures for Feature Extraction in ASR. Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010). Proceedings of Interspeech. Makuhari, Chiba: International Speech Communication Association, 2010. no. 9, p. 1201-1204. ISBN: 978-1-61782-123-3. ISSN: 1990-9772.
Type
conference paper
Language
English
Authors
Grézl František, Ing., Ph.D., DCGM (FIT)
Karafiát Martin, Ing., Ph.D., DCGM (FIT)
Abstract

The paper is on the incorporation of Bottle-Neck features into hierarchical architecture of classifiers. This architecture was used for feature extraction for LVCSR of meetings and the resulting features were evaluated on NIST RT'05 and RT'07 test sets.

Keywords

Speech recognition, Feature extraction, Neural network architecture

URL
Annotation

This paper presents the use of neural net hierarchy for feature extraction in ASR. The recently proposed Bottle-Neck feature extraction is extended and used in hierarchical structures to enhance the discriminative property of the features. Although many ways of hierarchical classification/feature extraction have been proposed, we restricted ourselves to use the outputs of the first stage neural network together with its inputs. This approach is evaluated on meeting speech recognition using RT'05 and RT'07 test sets. The evaluated hierarchical feature extraction brings consistent improvement over the use of just the first level neural net.

Published
2010
Pages
1201–1204
Journal
Proceedings of Interspeech, vol. 2010, no. 9, ISSN 1990-9772
Proceedings
Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)
Conference
Interspeech Conference
ISBN
978-1-61782-123-3
Publisher
International Speech Communication Association
Place
Makuhari, Chiba
BibTeX 
@inproceedings{BUT35026,
  author="František {Grézl} and Martin {Karafiát}",
  title="Hierarchical Neural Net Architectures for Feature Extraction in ASR",
  booktitle="Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)",
  year="2010",
  journal="Proceedings of Interspeech",
  volume="2010",
  number="9",
  pages="1201--1204",
  publisher="International Speech Communication Association",
  address="Makuhari, Chiba",
  isbn="978-1-61782-123-3",
  issn="1990-9772",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/grezl_interspeech2010_IS100741.pdf"
}
Projects
Recognition and presentation of multimedia data, BUT, Vnitřní projekty VUT, FIT-S-10-2, 2010, start: 2010-04-01, end: 2010-12-31, completed
Security-Oriented Research in Information Technology, MŠMT, Institucionální prostředky SR ČR (např. VZ, VC), MSM0021630528, start: 2007-01-01, end: 2013-12-31, running
Speech Recognition under Real-World Conditions, GACR, Standardní projekty, GA102/08/0707, start: 2008-01-01, end: 2011-12-31, completed
Theory and applications of phoneme posterior estimation in speech processing, GACR, Doktorské granty, GP102/09/P635, start: 2009-01-01, end: 2011-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top