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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Jan, J.: Číslicová filtrace, analýza a restaurace signálů. Vutium (2002) ISBN 80-214-1558-4
Karafiát, M., Grézl, F., Schwarz, P., Burget, L., Černocký, J.: Robust heteroscedastic Linear Discriminant Analysis and LCRC Posterior Features in Meeting Data Recognition. LNCS, pp. 275–284. Springer, Heidelberg (2007) ISBN 978-3-540-69267-6
Szöke, I., Schwarz, P., Matějka, P., Burget, L., Karafiát, M., Fapšo, M., Černocký, J.: Comparison of Keyword Spotting Approaches for Informal Continuous Speech. In: Proceedings of Interspeech 2005 – Eurospeech (2005) ISSN 1018-4074
Bishop, C.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006) ISBN 0-38-731073-8
Kontár, S.: Paralelní trénování neuronových sítí pro rozpoznávání řeči. FIT VUT Brno, diplomová práce (2006)
Pethick, M., Liddle, M., Werstein, P., Huang, Z.: Parallelization of a Backpropagation Neural Network on a Cluster Computer. In: Parallel and Distributed Computing and Systems. IASTED/ACTA Press (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Veselý, K., Burget, L., Grézl, F. (2010). Parallel Training of Neural Networks for Speech Recognition. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2010. Lecture Notes in Computer Science(), vol 6231. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15760-8_56
Download citation
DOI: https://doi.org/10.1007/978-3-642-15760-8_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15759-2
Online ISBN: 978-3-642-15760-8
eBook Packages: Computer ScienceComputer Science (R0)