Detail publikačního výsledku

Parallel Training of Neural Networks for Speech Recognition

VESELÝ, K.; BURGET, L.; GRÉZL, F.

Original Title

Parallel Training of Neural Networks for Speech Recognition

English Title

Parallel Training of Neural Networks for Speech Recognition

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

The paper is on Parallel Training of Neural Networks for Speech Recognition. A new parallel-training tool TNet was designed andoptimized for multiprocessor computers. The training acceleration rates are reportedon a phoneme-state classification task.

English abstract

The paper is on Parallel Training of Neural Networks for Speech Recognition. A new parallel-training tool TNet was designed andoptimized for multiprocessor computers. The training acceleration rates are reportedon a phoneme-state classification task.

Keywords

neural network, phoneme classification, posterior features, backpropagationtraining, data parallelization

Key words in English

neural network, phoneme classification, posterior features, backpropagationtraining, data parallelization

Authors

VESELÝ, K.; BURGET, L.; GRÉZL, F.

RIV year

2011

Released

06.09.2010

Publisher

Springer Verlag

Location

Brno

ISBN

978-3-642-15759-2

Book

Prof. Text, Speech and Dialogue 2010

Edition

LNAI 6231

ISBN

0302-9743

Periodical

Lecture Notes in Computer Science

Volume

2010

Number

9

State

Federal Republic of Germany

Pages from

439

Pages to

446

Pages count

8

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2010/vesely_tsd2010.pdf

Full text in the Digital Library

http://hdl.handle.net/

BibTex

@inproceedings{BUT35731,
  author="Karel {Veselý} and Lukáš {Burget} and František {Grézl}",
  title="Parallel Training of Neural Networks for Speech Recognition",
  booktitle="Prof. Text, Speech and Dialogue 2010",
  year="2010",
  series="LNAI 6231",
  journal="Lecture Notes in Computer Science",
  volume="2010",
  number="9",
  pages="439--446",
  publisher="Springer Verlag",
  address="Brno",
  isbn="978-3-642-15759-2",
  issn="0302-9743",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/vesely_tsd2010.pdf"
}