Implementing a Fuzzy Relational Neural Network for Phonetic Automatic Speech Recognition

  • Carlos Alberto Reyes Garcia
  • Wyllis Bandler
Part of the International Series in Intelligent Technologies book series (ISIT, volume 7)


In this chapter we present the implementation of a speech recognizer based on a fuzzy relational neural network model. In the model, the input acoustic phonetic features are represented by their respective fuzzy membership values to linguistic properties. The membership values are calculated with Π functions, and dense trapezoidal functions. The weights of the connections between input and output nodes are described in terms of their fuzzy relations. The output values are obtained by the use of the max-min composition, and are given in terms of fuzzy class membership values. The learning algorithm used is a modified version of the gradient-descent back-propagation algorithm following the model described by Pedrycz in [3]. Some results are presented as well.


Membership Function Output Node Input Feature Fuzzy Neural Network Recognition Score 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Pal, S.K., “Multilayer Perceptron, Fuzzy Sets, and Classification,” in IEEE Trans. on Neural Networks, vol 3, No 5, Sep 1992, pp 683–697.Google Scholar
  2. [2]
    Pal, S.K. and Mandai, D.P., “Linguistic Recognition Systems Based on Approximated Reasoning,” in Information Science, vol 61, No 2, 1992, pp 135–161.Google Scholar
  3. [3]
    Pedrycz, W., “Neurocomputations in Relational Systems,” in IEEE Trans, on Pattern Analysis and Mack Intelligence, vol 13, No 3, Mar 91, pp 289–296.Google Scholar
  4. [4]
    Keller, J.M., and Hunt, DJ., “Incorporating Fuzzy Membership Functions into the Perceptron Algorithm,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol PAMI-7, No 6, Nov 85, pp 693–699.Google Scholar
  5. [5]
    Zadeh, L.A., “Fuzzy Sets,” Inform. Contr., vol 8, 1965, pp 338–353.MathSciNetzbMATHCrossRefGoogle Scholar
  6. [6]
    Zadeh, L.A., “Fuzzy Logic and Approximated Reasoning,” in Synthese, 30, 1977, pp 407–428.CrossRefGoogle Scholar
  7. [7]
    Kandel, A., Fuzzy Techniques in Pattern Recognition, John Wiley & Sons, New York, 1982.zbMATHGoogle Scholar
  8. [8]
    Nath, A.K., Lee, T.T., “On the Design of a Classifier with Linguistic Variables as Inputs”, in Fuzzy Sets and Systems II, 1983, pp 265–286.Google Scholar
  9. [9]
    Zadeh, L.A., “The Concept of Linguistic Variable and its Application to Approximate Reasoning” -II, Information Sciences 8, 1977, pp 301–357.MathSciNetCrossRefGoogle Scholar
  10. [10]
    Park, D., Cae, Z., and Kandel, A., “Investigations on the Applicability of Fuzzy Inference,” in Fuzzy Sets and Systems, vol 49, 1992, pp 151–169.Google Scholar
  11. [11]
    Zadeh, L.A., “A fuzzy algorithmic approach to the deffinition of complex or imprecise concepts”, in Internationaljournal of Man-Machine Studies, (1976)8., pp 249–291.Google Scholar
  12. [12]
    Kosko, B., Neural Networks and Fuzzy Systems, Prentice Hall, New Jersey, 1992.zbMATHGoogle Scholar
  13. [13]
    Pedrycz, W., “Fuzzy Neural Networks with Reference Neurons as Pattern Classifiers,” in IEEE Trans. on Neural Networks, vol 3, No 5, Sept 92, pp 770–775.Google Scholar
  14. [14]
    Kohonen, T., Self-Organization and Associative Memory, Springer-Verlag, New York, 1989.Google Scholar
  15. [15]
    Cox, E., “Integrating Fuzzy Logic into Neural Nets,” in Al Expert, June 1992, pp 43–47.Google Scholar
  16. [16]
    Kohonen, T., Kangas, J., Laaksonen, J. and Torkkola, K., “The Learning Vector Quantization Program Package,” Version 2.1, Helsinki University of Technology, Lab. of Comp, and Info. Sci., SF-021150 Espoo, 1992.Google Scholar
  17. [17]
    Reyes, C.A. and Bandler, W.,“Una Introduccion al Reconocimiento Automatico del Habla,” Technical Report, Dept. of CS, FSU, 93–041, Tallahassee, Fl, 1992.Google Scholar
  18. [18]
    Bandler, W. and Kohout, L.J., “Mathematical Relations,” in Sing, Mandan G., editor, Systems & Control Encyclopedia, Pergamon Press, Oxford, 1987, pp 4000–4008.Google Scholar
  19. [19]
    Bandler, W. and Kohout, L.J., “Fuzzy Relational Products as a tool for analysis and artificial systems,” in P.P. Wang, and S.K. Chang, editors, Fuzzy Sets: Theory and Applications to Policy Analysis and Information Systems, Plenum Press, New York and London, 1980, pp 341–367.Google Scholar

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • Carlos Alberto Reyes Garcia
    • 1
  • Wyllis Bandler
    • 2
  1. 1.Instituto Tecnologico de ApizacoUniversidad Autonoma de Tlaxcala, CONACYTMexico
  2. 2.Department of Computer ScienceFlorida State UniversityTallahasseeUSA

Personalised recommendations