Článek ve sborníku konference

 
Veselý, K., Burget, L., Grézl, F.: Parallel Training of Neural Networks for Speech Recognition, In: Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010), Makuhari, Chiba, JP, ISCA, 2010, s. 2934-2937, ISSN 1990-9772
Jazyk publikace:angličtina
Název publikace:Parallel Training of Neural Networks for Speech Recognition
Název (cs):Paralelní trénování neuronových sítí pro rozpoznávání řeči
Strany:2934-2937
Sborník:Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)
Konference:Interspeech 2010
Místo vydání:Makuhari, Chiba, JP
Rok:2010
Časopis:Proceedings of Interspeech, roč. 2010, č. 9, FR
ISSN:1990-9772
Vydavatel:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2010/vesely_interspeech2010_IS100045.pdf [PDF]
Klíčová slova
Artificial Neural Network, GPU, CUDA, Phoneme Classification, Fast Training
Anotace
Článek pojednává o paralelním trénování neuronových sítí pro rozpoznávání řeči, založeném na ANN trénikovém postupu.
Abstrakt
In this paper we describe parallel implementation of ANN training procedure based on block mode back-propagation learning algorithm. Two different approaches to parallelization were implemented. The first is data parallelization using POSIX threads, it is suitable for multi-core computers. The second is node parallelization using high performance SIMD architecture of GPU with CUDA, suitable for CUDA enabled computers. We compare the speed-up of both approaches by learning typically-sized network on the real-world phoneme-state classification task, showing nearly 10 times reduction when using CUDA version, while the 8-core server with multi-thread version gives only 4 times reduction. In both cases we compared to an already BLAS optimized implementation. The training tool will be released as Open-Source software under project name TNet.
BibTeX:
@INPROCEEDINGS{
   author = {Karel Veselý and Lukáš Burget and František Grézl},
   title = {Parallel Training of Neural Networks for Speech Recognition},
   pages = {2934--2937},
   booktitle = {Proceedings of the 11th Annual Conference of the
	International Speech Communication Association (INTERSPEECH
	2010)},
   journal = {Proceedings of Interspeech},
   volume = {2010},
   number = {9},
   year = {2010},
   location = {Makuhari, Chiba, JP},
   publisher = {International Speech Communication Association},
   ISSN = {1990-9772},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9364}
}