Radial Basis Functions for Speech Recognition

  • Yoshua Bengio
Conference paper
Part of the NATO ASI Series book series (volume 75)


the purpose of this paper is to study the application of Radial Basis Functions (RBF) to automatic speech recognition. Results of several experiments with these networks on the recognition of phonemes for the TIMIT database are presented, including an experiment on a recurrent network of RBFs.


Radial Basis Function Automatic Speech Recognition Output Weight Recurrent Network Radial Basis Function 
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.
    Bengio Y., Cardin R., De Mori R. & Merlo E. (1989a), “Programmable Execution of Multi-Layered Networks for Automatic Speech Recognition”, in Communications of the Association of Computing Machinery, February 1989, vol. 32, number 2, pp. 195–199.Google Scholar
  2. 2.
    Bengio Y., Gori M. & De Mori R. (1989c), “BPS: a Learning Algorithm for Capturing the Dynamic Nature of Speech”, in the Proceedings of the International Joint Conference on Neural Networks 1989, pp. II–417 – II-424.Google Scholar
  3. 3.
    Bengio Y. & De Mori R. (1989), “Use of Multilayer Networks for the Recognition of Phonetic Features and Phonemes”, in Computational Intelligence, 5, pp. 134–141.CrossRefGoogle Scholar
  4. 4.
    Bengio Y., Cardin R., De Mori R. (1990), “Speaker Independent Speech Recognition with Neural Networks and Speech Knowledge”, in Advances in Neural Information Processing Systems 2, ed. D.S. Touretzky, Morgan Kaufmann Publishers.Google Scholar
  5. 5.
    Broomhead D.S. & Lowe D. (1988), “Multivariable functional interpolation and adaptive networks”, Complex Systems, 2: pp. 321–355.zbMATHMathSciNetGoogle Scholar
  6. 6.
    Garofolo J.S. (1988), “Getting started with the DARPA TIMIT CD-ROM: an acoustic phonetic continuous speech database”, National Institute of Standards and Technology (NIST), Gaithersburgh, MD.Google Scholar
  7. 7.
    Kruschke J.K. (1990), “ALCOVE: a connectionist model of category learning”, Technical Report 19, Cognitive Science Program, Indiana University.Google Scholar
  8. 8.
    Lee K.F. & Hon H.W. (1989), “Speaker-Independent Phone Recognition Using Hidden Markov Models”, IEEE Trans. on ASSP, vol. 37, no. 11, pp. 1641–1648.CrossRefGoogle Scholar
  9. 9.
    Leung H.C. & Zue V. (1990), “Phonetic classification using multi-layered perceptrons”, ICASSP 90, pp.525–528.Google Scholar
  10. 10.
    Mel B.W. & Koch C. (1990), “Sigma-Pi Learning: A Model for Associative Learning in Cerebral Cortex”, Advances in Neural Networks Information Processing Systems 2, ed. D.S. Touretzky, Morgan Kauffman.Google Scholar
  11. 11.
    Pearlmutter B.A. (1989), “Learning state space trajectories in recurrent neural networks”, Neural Computation, vol. 1, no. 2, pp.263–269.CrossRefGoogle Scholar
  12. 12.
    Penrose R. (1955), “A generalized inverse for matrices”, Proc. Cambridge Philos. Soc., 51: pp.406–513.CrossRefzbMATHMathSciNetGoogle Scholar
  13. 13.
    Poggio T. & Girosi F. (1989), “A Theory of Networks for Approximation and Learning”, MIT A.I. Memo No. 1140.Google Scholar
  14. 14.
    Robinson T. & Fallside F. (1990), “Phoneme recognition from the TIMIT database using recurrent error propagation networks”, CUED/F-INFEG/TR.42, Cambridge University Engineering dept.Google Scholar
  15. 15.
    Rumelhart D.E., Hinton G., Williams R.J. (1986), “Learning internal representation by error propagation”, in Parallel Distributed Processing, vol. 1, (eds. Rumelhart & McClelland), Bradford Books/MIT Press.Google Scholar
  16. 16.
    Waibel A., Hanazawa T., Hinton G., Shikano K. & Lang K. (1987), “Phoneme Recognition using Time Delay Neural Networks”, Technical Report TR-I-0006, ATR Interpreting Telephony Research Laboratories.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Yoshua Bengio
    • 1
  1. 1.School of Computer ScienceMcGill UniversityMontrealCanada

Personalised recommendations