Faculty of Information Technology, BUT

Publication Details

Hierarchical Neural Net Architectures for Feature Extraction in ASR

GRÉZL František and KARAFIÁT Martin. Hierarchical Neural Net Architectures for Feature Extraction in ASR. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010). Makuhari, Chiba: International Speech Communication Association, 2010, pp. 1201-1204. ISBN 978-1-61782-123-3. ISSN 1990-9772.
Czech title
Hierarchické architektury neuronových sítí pro výpočet příznaků v rozpoznávání řeči
Type
conference paper
Language
english
Authors
URL
Keywords
Speech recognition, Feature extraction, Neural network architecture
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.
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 2010, Tokyo, JP
ISBN
978-1-61782-123-3
Publisher
International Speech Communication Association
Place
Makuhari, Chiba, JP
BibTeX
@INPROCEEDINGS{FITPUB9363,
   author = "Franti\v{s}ek Gr\'{e}zl and Martin Karafi\'{a}t",
   title = "Hierarchical Neural Net Architectures for Feature Extraction in ASR",
   pages = "1201--1204",
   booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)",
   journal = "Proceedings of Interspeech",
   volume = 2010,
   number = 9,
   year = 2010,
   location = "Makuhari, Chiba, JP",
   publisher = "International Speech Communication Association",
   ISBN = "978-1-61782-123-3",
   ISSN = "1990-9772",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9363"
}
Back to top