Conference paper

VESELÝ Karel. Parallel training of neural networks for speech recognition. In: Proceedings of the 16th Conference STUDENT EEICT 2010. Brno: Brno University of Technology, 2010, pp. 74-76. ISBN 978-80-214-4078-4.
Publication language:english
Original title:Parallel training of neural networks for speech recognition
Title (cs):Paralelní trénování neuronových sítí pro rozpoznávání řeči
Pages:74-76
Proceedings:Proceedings of the 16th Conference STUDENT EEICT 2010
Conference:Student EEICT 2010
Series:Volume 3
Place:Brno, CZ
Year:2010
ISBN:978-80-214-4078-4
Publisher:Brno University of Technology
URL:http://www.feec.vutbr.cz/EEICT/2010/sbornik/02-Magisterske_projekty/08-Grafika_a_multimedia/10-xvesel39.pdf [PDF]
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2010/vesely_EEITC_2010_39.pdf [PDF]
Keywords
neural network, phoneme classification, posterior features, backpropagation training, data parallelization
Annotation
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.
Abstract
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.
BibTeX:
@INPROCEEDINGS{
   author = {Karel Veselý},
   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 = {http://www.fit.vutbr.cz/research/view_pub.php?id=9331}
}

Your IPv4 address: 54.81.112.187
Switch to IPv6 connection

DNSSEC [dnssec]