Publication result detail

The Role of Neural Network Size in TRAP/HATS Feature Extraction

GRÉZL, F.

Original Title

The Role of Neural Network Size in TRAP/HATS Feature Extraction

English Title

The Role of Neural Network Size in TRAP/HATS Feature Extraction

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

This article examines the performance of TRAP/HATS based probabilistic features in ASR. The sizes of neural networks in both stages of processing are changed and the influence is evaluated.

English abstract

This article examines the performance of TRAP/HATS based probabilistic features in ASR. The sizes of neural networks in both stages of processing are changed and the influence is evaluated.

Keywords

Neural networks, feature extraction, probabilistic features

Key words in English

Neural networks, feature extraction, probabilistic features

Authors

GRÉZL, F.

RIV year

2012

Released

01.09.2011

Publisher

Springer Verlag

Location

Plzeň

ISBN

978-3-642-23537-5

Book

Proceedings Text, Speech and Dialogue 2011

Edition

LNAI 6836

ISBN

0302-9743

Periodical

Lecture Notes in Computer Science

Volume

2011

Number

9

State

Federal Republic of Germany

Pages from

315

Pages to

322

Pages count

8

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2011/grezl_tsd2011.pdf

Full text in the Digital Library

http://hdl.handle.net/

BibTex

@inproceedings{BUT76446,
  author="František {Grézl}",
  title="The Role of Neural Network Size in TRAP/HATS Feature Extraction",
  booktitle="Proceedings Text, Speech and Dialogue 2011",
  year="2011",
  series="LNAI 6836",
  journal="Lecture Notes in Computer Science",
  volume="2011",
  number="9",
  pages="315--322",
  publisher="Springer Verlag",
  address="Plzeň",
  isbn="978-3-642-23537-5",
  issn="0302-9743",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/grezl_tsd2011.pdf"
}