Detail publikace

Parallel training of neural networks for speech recognition

KONTÁR, S.

Originální název

Parallel training of neural networks for speech recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In speech recognition, forward multi-layer neural networks are used as classifiers for phoneme recognizers, for speech parameterization, in language models, and for language or speaker recognition. This paper discusses possibilities of training forward multi-layer neural networks using parallel algorithms. The need for parallel training of neural networks is caused by huge quantity of training data used in speech recognition. Synchronous and asynchronous variants of the training are discussed and experimental results are reported on a real speech processing task.

Klíčová slova

Artificial neural networks, speech recognition, parallel training algorithms

Autoři

KONTÁR, S.

Rok RIV

2006

Vydáno

26. 9. 2006

Nakladatel

Brno University of Technology

Místo

Brno

ISBN

80-214-3195-4

Kniha

Proc. 12th International Conference on Soft Computing MENDEL'06

Strany od

6037

Strany do

6042

Strany počet

6

BibTex

@inproceedings{BUT22372,
  author="Stanislav {Kontár}",
  title="Parallel training of neural networks for speech recognition",
  booktitle="Proc. 12th International Conference on Soft Computing MENDEL'06",
  year="2006",
  pages="6",
  publisher="Brno University of Technology",
  address="Brno",
  isbn="80-214-3195-4"
}