Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

(167.2KB)
This is an Open Access publication published under CSC-OpenAccess Policy.
Publications from CSC-OpenAccess Library are being accessed from over 74 countries worldwide.
Word Recognition in Continuous Speech and Speaker Independent by Means of Recurrent Self-Organizing Spiking Neurons
Tarek Behi, Najet Arous, Noureddine Ellouze
Pages - 215 - 226     |    Revised - 01-11-2011     |    Published - 15-12-2011
Volume - 5   Issue - 5    |    Publication Date - November / December 2011  Table of Contents
MORE INFORMATION
KEYWORDS
Word Recognition, kohonen Map, Self-Organizing Spiking Neurons, leaky Integrators Neurons, Recurrent Spiking SOM
ABSTRACT
Artificial neural networks have been applied successfully in many static systems 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. Speech, being a temporal form of sensory input, is a natural candidate for investigating temporal coding in neural networks. It is only through comprehension of the temporal relationship between different sounds which make up a spoken word or sentence that speech becomes intelligible. In fact we present in this paper presents three variants of self-organizing maps (SOM), the Leaky Integrators Neurons (LIN), the Spiking_SOM (SSOM) and the recurrent Spiking_SOM (RSSOM) models. The proposed variants 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 case study of the proposed SOM variants is word recognition in continuous speech and speaker independent. The proposed SOM variants show good robustness and high word recognition rates.
CITED BY (1)  
1 Schmuker, M., Pfeil, T., & Nawrot, M. P. (2014). A neuromorphic network for generic multivariate data classification. Proceedings of the National Academy of Sciences, 111(6), 2081-2086.
1 Google Scholar 
2 CiteSeerX 
3 refSeek 
4 Scribd 
5 SlideShare 
6 PdfSR 
1 W. Maass, M. Schmitt. “On the complexity of learning for a spiking neuron”. In COLT’97, Conf.on Computational Learning Theory, ACM Press, 1997. pp. 54–61.
2 W. Gerstner. “What´s different with spiking neurons”. In Henk Mastebroek and Hans Vos,editors, Plausible Neural Networks for Biological Modelling, Kluwer Academic Publishers;2001.pp. 23–48.
3 W. Maass, C. M Bishop. “Pulsed Neural Networks”. MIT Press, 1999.
4 R. Kempter, W. Gerstner. J. L VanHemmen and H. Wagner. “Extracting oscillations: Neuronal coincidence detection with noisy periodic spike input”. Neural Comput., vol. 10, pp. 1987-2017,1998.
5 W. R Softky, C. Koch. “The highly irregular firing of cortical cells is inconsistent with temporal integration of random EPSPs”. J. Neurosci. Vol. 13, pp. 334–350, 1993.
6 F. Santiage , G. Alex, S. Jurgen. “Phoneme recognition with BLSIM-CIC”. 2008.
7 S. Durand. “Réseaux neuromimétiques spatio-temporels pour l’organisation des sens. Application à la parole. Dans Actes Rencontres Nationales des Jeunes chercheurs en Intelligence Artificielle. Marseille, 1994.
8 S. Durand. “TOM, une architecture connexionniste de traitement de séquence. Application à la reconnaissance de la parole”. PhD thesis Université Henri Poincaré, Nancy I ; 1995.
9 P. Danilo, Mandic, A. Jonathon. “Chambers, Recurrent Neural Networks for Prediction”, John Wiley and Sons Ltd, 2001.
10 G Vaucher. “Un modèle de neurone artificiel conçu pour l’apprentissage non supervise de séquences d’événements asynchrones”. In Revue VALGO, ISSN 1243-4825, Vol 1, pp. 66–107,1993.
11 T. Behi, N. Arous. “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, 2008.
12 T. Behi, N. Arous. “Modèles auto-organisateur à apprentissage spatio-temporels Evaluation dans le domaine de la classification phonémique”. Cinquième conférence internationale JTEA2008, Hammamet-Tunisie , 2008.
13 R. Brette. “Modèles Impulsionnels de Réseaux de Neurones Biologiques”. PhD Thesis,University of Cerveau-Cognition – Comporteme, 2003.
14 14 T, Kohonen. “Self_Organized Formation of Topologically Correct Feature Maps”. Biological Cybernetics. Vol.43, pp. 59-69,1982.
15 N. Arous. “Hybridation des Cartes de Kohonen par les algorithmes génétiques pour la classification phonémique. PhD Thesis Ecole Nationale d’ingénieurs de Tunis , 2003.
16 S. Haykin. “Neural Network A Comprehensive Foundation”, Prentice Hall Upper Saddle River,New Jersey, 1999.
17 T. Kohonen. “Self-organizing map”, third edition, Springer, 2003.
18 W. Maass. “Computing with spiking neurons”.In Maass, W. and Bishop, C. M., editors, Pulsed Neural Networks, chapter 2, MIT-Press., pp. 55-85 (1998)
19 W. Maass, C. M. Bishop. “Pulsed Neural Networks”. The MIT Press, 1st edition, Cambridge,1998.
20 M. Varsta, J. Heikkonen and R; Milan. “A recurrent self-organizing map for temporal sequence processing”. Proc. Int. Conf. on Artificial Neural Networks (ICANNP'P97), Lausanne,Switzerland, 1997.
21 T. Koskela, M. Varsta, J. Heikkonen, K. Kaski. “Time Series prediction using recurrent SOM with local linear models”. International Journal of Knowledge-based Intelligent Engineering Systems,2(1), : 60-68, 1998.
22 J.G. Taylor. “Temporal patterns and leaky integrator neurons”. Proc. Int. Conference. Neural Networks (ICNN'90), Paris, 1990.
23 T. koskela, M. varsta. “Recurrent SOM with local linear models in time series prediction”, PhD Thesis, University of Helsinki university of technologie-labo of computational engineeringFinland,April 1998.
24 M. Varsta. “Temporal sequence processing using recurrent SOM”, PhD Thesis, University of Helsinki university of technologie-labo of computational engineering-Finland, 1998.
25 T. Voegtlin. “Réseaux de neurones et autoréférence”, PhD Thesis, University of lumière lyon II,2004.
26 N. Arous, N. Ellouze. “Phoneme classification accuracy improvements by means of new variants of unsupervised learning neural networks”, 6th World Multiconference on Systematics,Cybernetics and Informatics, Floride, USA, 2002.
27 N. Arous, N. Ellouze. “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, vol. 51, pp. 225 – 235,2003.
28 J. Garofalo, L. Lamel, W. Fisher, J. Fiscus, D. Pallett, N. Dahlgren and V. Zue. “TIMIT acousticphonetic continuous speech corpus”, Linguistic Data Consort, 2005.
29 V. Zue, S. Seneff, J. Glass. “Speech database development at MIT, TIMIT, and beyond”,Speech Commun, vol. 9, pp. 351–356, 1990.
Mr. Tarek Behi
ENIT - Tunisia
tarekbehi@gmail.com
Dr. Najet Arous
ENIT - Tunisia
Professor Noureddine Ellouze
ENIT - Tunisia