Publication detail

Hierarchical Neural Net Architectures for Feature Extraction in ASR

GRÉZL, F. KARAFIÁT, M.

Original Title

Hierarchical Neural Net Architectures for Feature Extraction in ASR

Type

article in a collection out of WoS and Scopus

Language

English

Original 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

Authors

GRÉZL, F.; KARAFIÁT, M.

RIV year

2010

Released

26. 9. 2010

Publisher

International Speech Communication Association

Location

Makuhari, Chiba

ISBN

978-1-61782-123-3

Book

Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)

ISBN

1990-9772

Periodical

Proceedings of Interspeech

Year of study

2010

Number

9

State

French Republic

Pages from

1201

Pages to

1204

Pages count

4

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2010/grezl_interspeech2010_IS100741.pdf

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"
}