Detail publikace

Parallel training of neural networks for speech recognition

VESELÝ, K.

Originální název

Parallel training of neural networks for speech recognition

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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

Klíčová slova

neural network, phoneme classification, posterior features, backpropagation training, data parallelization

Autoři

VESELÝ, K.

Rok RIV

2010

Vydáno

29. 4. 2010

Nakladatel

Brno University of Technology

Místo

Brno

ISBN

978-80-214-4078-4

Kniha

Proceedings of the 16th Conference STUDENT EEICT 2010

Edice

Volume 3

Strany od

74

Strany do

76

Strany počet

3

URL

https://www.fit.vut.cz/research/publication/9331/

BibTex

@inproceedings{BUT35831,
  author="Karel {Veselý}",
  title="Parallel training of neural networks for speech recognition",
  booktitle="Proceedings of the 16th Conference STUDENT EEICT 2010",
  year="2010",
  series="Volume 3",
  pages="74--76",
  publisher="Brno University of Technology",
  address="Brno",
  isbn="978-80-214-4078-4",
  url="https://www.fit.vut.cz/research/publication/9331/"
}