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

English Title

Hierarchical Neural Net Architectures for Feature Extraction in ASR

Type

conference paper

Language

en

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.

English 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

RIV year

2010

Released

26.09.2010

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)

Edition

NEUVEDEN

Edition number

NEUVEDEN

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",
  annote="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.",
  address="International Speech Communication Association",
  booktitle="Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)",
  chapter="35026",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  journal="Proceedings of Interspeech",
  number="9",
  year="2010",
  month="september",
  pages="1201--1204",
  publisher="International Speech Communication Association",
  type="conference paper"
}