Advertisement

A Speaker Independent Arabic Isolated Spoken Digits Recognition System Using Fuzzy Kohonen Clustering Network

  • J. Elmalek
  • R. Tourki
Conference paper

Abstract

A Fuzzy Kohonen Network, which is capable of recognizing isolated Arabic spoken number speaker independently is described. The Fuzzy Kohonen Clustering Network (FKCN) algorithm, is based on the integration of Fuzzy C-Means (FCM) and Kohonen Clustering Network (KCN). FKCN is unsupervised, non-sequential, and uses fuzzy membership values from FCM as learning rates. Simulation results clearly indicate the superiority in recognition accuracy performance of FKCN when compared to that obtained for FCM, KCN and the conventional LBG (Linde-Buzo-Gray).

Keywords

Feature Vector Weight Vector Speech Recognition System Small Positive Constant Automatic Speech Recognition System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Mouria, B. F., Brahem, R., Nejma, A. M: Syrapa: An automatic Arabic phoneme recognition system. 2nd IMACS International Multiconference CES A′98, Nabeul-Hammamet, Tunisia, vol. 4, pp. 196–200, 1998Google Scholar
  2. [2]
    Jamaa, M., Alimi, A. M: Recognition of spoken isolated Arabic words with the Beta Fuzzy Neural Network. 2nd IMACS International Multiconference CESA′98, Nabeul-Hammamet, Tunisia, vol. 4, pp. 348–351, 1998Google Scholar
  3. [3]
    Belhaj, N., Boukadida, F., Ellouze, N.: Sapia:Expert system in Automatic segmentation and labelling of Arabic speech. 2nd IMACS International Multiconference CESA′98, Nabeul-Hammamet, Tunisia, vol. 4, pp. 201–203, 1998Google Scholar
  4. [4]
    Sayoud, H., Selmane, M. K.: inter and intra-speaker variability of some phonetic parameters in standard Arabic. Classification in speaker recognition. 2nd IMACS International Multiconference CESA′98, Nabeul-Hammamet, Tunisia, vol. 4, pp. 216–219, 1998Google Scholar
  5. [5]
    Oweiss, K., Abdel, A. O.: Performance evaluation of the time-delay fuzzy neural networks for isolated word recognition. International Symposium on Neuro-Fuzzy Systems, pp. 203–211, 1996.Google Scholar
  6. [6]
    Alotaibi, Y. A., Shahsavri, M. M.: Speech recognition. IEEE Potentials, pp. 23–28, Feb-March 1998.Google Scholar
  7. [7]
    Kohonen, T.: Self-organization and associative memory. Springer-verlag, 1988.Google Scholar
  8. [8]
    Kohonen, T.: Self-organization map. Proc. of IEEE, vol. 78, no. 9, pp. 1464–1480, 1990.CrossRefGoogle Scholar
  9. [9]
    Kohonen, T.: Self-organizing maps. Berlin, Springerverlag, 1995CrossRefGoogle Scholar
  10. [10]
    Fritzke, B.: Some competitive learning methods. Draft documend, available http:/www.neuroinformatik.ruhur-uni-bochum.de/ini/VDM/research/gsn/demogng.
  11. [11]
    Martinetz, T. M., Schulten, K. J.: Topology representing networks. Neural Networks, vol. 7, no.3, pp. 507–522, 1994.CrossRefGoogle Scholar
  12. [12]
    Tsao, E. C., Bezdek, J. C., Pal, N. R.: Fuzzy Kohonen clustering network. Pattern Recognition, vol. 27, no. 5, pp. 757–764, 1994.CrossRefGoogle Scholar
  13. [13]
    Erwin, E., Obermayer, K., Schulten, K.: Self organizing maps: Ordering, convergence properties, and energy functions. Biol, Cybern, vol. 67, pp. 47–55, 1992.MATHCrossRefGoogle Scholar
  14. [14]
    Bezdek, J. C: Pattern Recognition with fuzzy objective function algorithms. Plenum, New York 1981.MATHCrossRefGoogle Scholar
  15. [15]
    Mcbratney, A. B., Moore, A. W.: Application of fuzzy sets to climatic classification, Agric. Forest Meteor. Vol.35, pp. 165–185, 1985.CrossRefGoogle Scholar
  16. [16]
    Choc, H., Jordan, J.: On the optimal choice of parameters in a fuzzy c-means algorithms. Proc. First IEEE conf. on Fuzzy systems, san Diego 1992.Google Scholar
  17. [17]
    Bezdek, J. C., Pal, N. R.: two soft relative of learning vector quantization.: Neural Networks, vol. 8, no. 5, pp. 729–743, 1995.CrossRefGoogle Scholar
  18. [18]
    Huntsberger, T., Ajjimarangsee, P.: Parallel self-organizing feature maps for unsupervised pattern recognition, Int. J. Gen. Syst, 16, pp. 357–372, 1989.CrossRefGoogle Scholar
  19. [19]
    Bezdek, J. C., Pal, N. R.: Generalization clustering networks and Kohonen’s self-organizing scheme. IEEE. Trans. Neural Networks, vol. 4, pp. 549–557, 1993.CrossRefGoogle Scholar
  20. [20]
    Karayiannis, N. B., Bezdek, J. C., Pal, N. R., Hathaway, R. J., Pai, P.: Repair to GLVQ: A new family of competitive learning schemes. IEEE Trans. Neural Networks. Vol. 7, pp. 1062–1071, 1996.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • J. Elmalek
    • 1
  • R. Tourki
    • 1
  1. 1.Faculty Of Sciences, Route De KairouanElectronics and Micro-Electronic LaboratoryMonastirTunisie

Personalised recommendations