Publication Details

Parallel training of neural networks for speech recognition

VESELÝ Karel. Parallel training of neural networks for speech recognition. In: Proceedings of the 16th Conference STUDENT EEICT 2010. Volume 3. Brno: Brno University of Technology, 2010, pp. 74-76. ISBN 978-80-214-4078-4.
Czech title
Paralelní trénování neuronových sítí pro rozpoznávání řeči
Type
conference paper
Language
english
Authors
Veselý Karel, Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

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

Abstract

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.

Annotation

The feed-forward multi-layer neural networks have significant importance in 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.

Published
2010
Pages
74-76
Proceedings
Proceedings of the 16th Conference STUDENT EEICT 2010
Series
Volume 3
Conference
Student EEICT 2010, Brno, CZ
ISBN
978-80-214-4078-4
Publisher
Brno University of Technology
Place
Brno, CZ
BibTeX 
@INPROCEEDINGS{FITPUB9331,
   author = "Karel Vesel\'{y}",
   title = "Parallel training of neural networks for speech recognition",
   pages = "74--76",
   booktitle = "Proceedings of the 16th Conference STUDENT EEICT 2010",
   series = "Volume 3",
   year = 2010,
   location = "Brno, CZ",
   publisher = "Brno University of Technology",
   ISBN = "978-80-214-4078-4",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9331"
}
Back to top