Detail publikace

Hierarchical Neural Net Architectures for Feature Extraction in ASR

GRÉZL, F. KARAFIÁT, M.

Originální název

Hierarchical Neural Net Architectures for Feature Extraction in ASR

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Speech recognition, Feature extraction, Neural network architecture

Autoři

GRÉZL, F.; KARAFIÁT, M.

Rok RIV

2010

Vydáno

26. 9. 2010

Nakladatel

International Speech Communication Association

Místo

Makuhari, Chiba

ISBN

978-1-61782-123-3

Kniha

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

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2010

Číslo

9

Stát

Francouzská republika

Strany od

1201

Strany do

1204

Strany počet

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"
}