IMPROVEMENT NEURAL NETWORKS USING 9WAVELETS FOR SPEECH RECOGNITION


Cite item

Full Text

Abstract

In the given paper a new method for improving neural networks is proposed. The method adds a module of inverse wavelet decomposition. Possibilities of using neural networks with the module for speech recognition problems are examined. The results of computational modeling on a PC are adduced.

About the authors

N I Chervjakov

K A Astapov

References

  1. Tebelskis J. Speech Recognition using Neural Networks: PhD thesis ... Doctor of Philosophy in Computer Science. School of Computer Science, Carnegie Mellon University. Pittsburgh, Pennsylvania, 1995.- 179 p.
  2. Lakhmi C., Jain L.C., Martin N.M. Fusion of Neural Networks, Fuzzy Systems and Genetic Algorithms: Industrial Applications. CRC Press, CRC Press LLC, 1998.-297 p.
  3. Handbook of neural network signal processing // Edited by Yu Hen Hu, Jenq-Neng Hwang. Boca Raton; London; New York, Washington D.C.: CRC press, 2001.-384 p.
  4. Principe J.C. Artificial Neural Networks. The Electrical Engineering Handbook // Ed. Richard C. Dorf. Boca Raton: CRC Press LLC, 2000. - 2719 p.
  5. Хайкин С. Нейронные сети: полный курс. Пер. с англ. М.: ООО «ИД Вильяме», 2006. - 1104 с.
  6. Добеши И. Десять лекций по вейвлетам. Ижевск: НИЦ «Регулярная и хаотическая динамика», 2001.-464 с.
  7. Haar A. Zur Theorie der Orthogonalen Funktionen- Systeme // Math. Ann. No. 69, 1910. - P. 331-371

Supplementary files

Supplementary Files
Action
1. JATS XML

Copyright (c) 2008 Chervjakov N.I., Astapov K.A.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies