We apologize for a recent technical issue with our email system, which temporarily affected account activations. Accounts have now been activated. Authors may proceed with paper submissions. PhDFocusTM
CFP last date
20 November 2024
Reseach Article

New variant of the Self Organizing Map in Pulsed Neural Networks to Improve Phoneme Recognition in Continuous Speech

by Tarek Behi, Najet Arous, Noureddine Ellouze
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 46 - Number 15
Year of Publication: 2012
Authors: Tarek Behi, Najet Arous, Noureddine Ellouze
10.5120/6987-9569

Tarek Behi, Najet Arous, Noureddine Ellouze . New variant of the Self Organizing Map in Pulsed Neural Networks to Improve Phoneme Recognition in Continuous Speech. International Journal of Computer Applications. 46, 15 ( May 2012), 34-40. DOI=10.5120/6987-9569

@article{ 10.5120/6987-9569,
author = { Tarek Behi, Najet Arous, Noureddine Ellouze },
title = { New variant of the Self Organizing Map in Pulsed Neural Networks to Improve Phoneme Recognition in Continuous Speech },
journal = { International Journal of Computer Applications },
issue_date = { May 2012 },
volume = { 46 },
number = { 15 },
month = { May },
year = { 2012 },
issn = { 0975-8887 },
pages = { 34-40 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume46/number15/6987-9569/ },
doi = { 10.5120/6987-9569 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:39:50.243783+05:30
%A Tarek Behi
%A Najet Arous
%A Noureddine Ellouze
%T New variant of the Self Organizing Map in Pulsed Neural Networks to Improve Phoneme Recognition in Continuous Speech
%J International Journal of Computer Applications
%@ 0975-8887
%V 46
%N 15
%P 34-40
%D 2012
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Speech recognition has gradually improved over the years, phoneme recognition in particular. Phoneme recognition plays very important role in speech processing. Phoneme strings are basic representation for automatic language recognition and it is proved that language recognition results are highly correlated with phoneme recognition results. Nowadays, many recognizers are based on Artificial neural networks have been applied successfully in speech recognition applications including multi-layer perceptrons, time delay neural network, recurrent neural network and self-organizing maps (SOM), but present some weaknesses if patterns involve a temporal component. Let's note for example in speech recognition or contextual information, where different of the time interval, is crucial for comprehension. In this paper, we propose a new variant SOM made of spiking neurons, with a view to emphasising the temporal aspect of the data which might serve as an input, in order to improve phoneme classification accuracy. The proposed variant, the Leaky Integrators Neurons, is like the basic SOM, however it represents the characteristic to modify the learning function and the choice of the best matching unit (BMU). The proposed SOM variant, show good robustness and high phoneme classification rates.

References
  1. Santiage, F. , Alex, G. and Jurgen, S. 2008. Phoneme recognition with BLSIM-CIC. In IDSIA.
  2. Durand, S. 1994. Réseaux neuromimétiques spatio-temporels pour l'organisation des sens. Application à la parole. Dans Actes Rencontres Nationales des Jeunes chercheurs en Intelligence Artificielle. Marseille.
  3. Durand, S. 1995. TOM, une architecture connexionniste de traitement de séquence. Application à la reconnaissance de la parole. PhD thesis, Université Henri Poincaré, Nancy I.
  4. Danilo, P. , Mandic. and Jonathon, A. 2001. Recurrent Neural Networks for Prediction, John Wiley and Sons Ltd.
  5. Vaucher, G. 1993. Un modèle de neurone artificiel conçu pour l'apprentissage non supervise de séquences d'événements asynchrones. In Revue VALGO, ISSN 1243-4825. 1, 66–107.
  6. Behi, T. and Arous, N. 2008. Modèle auto-organisateur à composante temporelle pour la reconnaissance de la parole continue. Huitième journée scientifiques des jeunes chercheurs en génie électrique et informatique, GEI2008, Sousse-Tunisie.
  7. Behi, T. and Arous N. 2008. Modèles auto-organisateur à apprentissage spatio-temporels Evaluation dans le domaine de la classification phonémique. Cinquième conférence internationale JTEA2008, Hammamet-Tunisie.
  8. Brette, R. 2003. Modèles Impulsionnels de Réseaux de Neurones Biologiques. Thèse de Doctorat, Ecole Doctorale Cerveau-Cognition – Comporteme.
  9. Maass, W. and Bishop, CM. 1999. Pulsed Neural Networks. MIT Press.
  10. Maass, W. and Schmitt, M. 1997. On the complexity of learning for a spiking neuron. In COLT'97, Conf. on Computational Learning Theory, ACM Press. 54–61.
  11. Kempter, R. , Gerstner, W. , Van Hemmen, JL. and Wagner, H. 1998. Extracting oscillations: Neuronal coincidence detection with noisy periodic spike input. Neural Comput. 10, 1987-2017.
  12. Softky, WR. and Koch, C. 1993. The highly irregular firing of cortical cells is inconsistent with temporal integration of random EPSPs. J. Neurosci. 13, 334–350.
  13. Kohonen, T. 1982. Self_Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics. 43, 59-69.
  14. Arous, N. 2003. Hybridation des Cartes de Kohonen par les algorithmes génétiques pour la classification phonémique. Thèse de Doctorat en Génie Electrique, Ecole Nationale d'ingénieurs de Tunis.
  15. Haykin, S. 1999. Neural Network A Comprehensive Foundation, Prentice Hall Upper Saddle River, New Jersey.
  16. Kohonen, T. 2003. Self-organizing map, third edition, Springer.
  17. Mozayyani, N. , Alanou, V. , Derfus, J. and Vaucher, G. 1995. A spatio-temporal data coding applied to kohonen maps, in Proceeding of International Conference on Artificial Neural Network. 75–79.
  18. Zouhour, N. , Laurent, B. and Frédéric, A. 2007. Spatio-temporal biologically inspired models for clean and noisy speech recognition Elsevier Science, Neurocomputing. 71, 131-136.
  19. Varsta, M. , Heikkonen, J. and Milan, R. 1997. A recurrent self-organizing map for temporal sequence processing. Proc. Int. Conf. on Artificial Neural Networks (ICANNP'P97), Lausanne, Switzerland. 421-426.
  20. Koskela, T. , Varsta, M. , Heikkonen, J. and Kaski, K. 1998. Time Series prediction using recurrent SOM with local linear models. International Journal of Knowledge-based Intelligent Engineering Systems. 2(1), 60-68.
  21. Koskela, T. , Varsta, M. , Heikkonen, J. and Kaski, K. 1998. Temporal sequence processing using recurrent SOM. KES. 1, 290-297
  22. Hammer, B. , Micheli, A. , Sperduti, A. and Strickert, M. 2004. A general framework for unsupervised processing of structured data Neurocomputing. 57, 3-35.
  23. Marc, S. and Barbara, H. 2005. Merge SOM for temporal data. In Neurocomputing. 64, 39-71.
  24. Salhi, M. S. , Arous, N. and Ellouze, N. 2009. Principal temporal extensions of SOM: Overview. International Journal of Signal Processing, Image Processing and Pattern Recognition. 2(4), 61-84.
  25. Maass, W. 1998. Computing with spiking neurons . In Maass, W. and Bishop, C. M. , editors, Pulsed Neural Networks, chapter 2, MIT-Press. 55-85.
  26. Maass, W. and Bishop, C. M. 1998. Pulsed Neural Networks. The MIT Press, 1st edition, Cambridge.
  27. Taylor, J. G. 1990. Temporal patterns and leaky integrator neurons. Proc. Int. Conf. Neural Networks (ICNN'90), Paris, 952-955.
  28. Koskela, T. and Varsta, M. 1998. Recurrent SOM with local linear models in time series prediction. Helsinki university of technologie-labo of computational engineering-Finland. (April 1998).
  29. Varsta, M. 1998. Temporal sequence processing using recurrent SOM. Helsinki university of technologie labo of computational engineering-Finland.
  30. Voegtlin, T. 2004. Réseaux de neurones et autoréférence. Thèse de Doctorat, université lumière lyon II.
  31. Arous, N. and Ellouze, N. 2002. Phoneme classification accuracy improvements by means of new variants of unsupervised learning neural networks, 6th World Multiconference on Systematics, Cybernetics and Informatics. Floride, USA, 14 – 18.
  32. Arous, N. and Ellouze, N. 2003. Cooperative supervised and unsupervised learning algorithm for phoneme recognition in continuous speech and speaker-independent context. Elsevier Science, Neurocomputing, Special Issue on Neural Pattern Recognition. 51, 225 – 235.
Index Terms

Computer Science
Information Sciences

Keywords

Kohonen Map Temporal Self Organizing Map Leaky Integrator Neurons Phoneme Classification.