Publication detail

Integrating recent MLP feature extraction techniques into TRAP architecture

GRÉZL, F. KARAFIÁT, M.

Original Title

Integrating recent MLP feature extraction techniques into TRAP architecture

English Title

Integrating recent MLP feature extraction techniques into TRAP architecture

Type

conference paper

Language

en

Original Abstract

The article shows the performance improvement and limitations of TRAP and HATS neural net systems for feature extraction in LVCSR when the bottel neck approach and phoneme states targets are introduced into them.

English abstract

The article shows the performance improvement and limitations of TRAP and HATS neural net systems for feature extraction in LVCSR when the bottel neck approach and phoneme states targets are introduced into them.

Keywords

TRAP processing, Bottle-Neck technique, subphoneme classes, LVCSR features

RIV year

2011

Released

27.08.2011

Publisher

International Speech Communication Association

Location

Florence

ISBN

978-1-61839-270-1

Book

Proceedings of Interspeech 2011

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

1229

Pages to

1232

Pages count

4

URL

Documents

BibTex


@inproceedings{BUT76438,
  author="František {Grézl} and Martin {Karafiát}",
  title="Integrating recent MLP feature extraction techniques into TRAP architecture",
  annote="The article shows the performance improvement and limitations of TRAP and HATS
neural net systems for feature extraction in LVCSR when the bottel neck approach
and phoneme states targets are introduced into them.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2011",
  chapter="76438",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  number="8",
  year="2011",
  month="august",
  pages="1229--1232",
  publisher="International Speech Communication Association",
  type="conference paper"
}