Skip to main content
SpringerLink
Log in

Improved Hidden Markov Models for Speech Recognition Through Neural Network Learning

  • Conference paper
From Statistics to Neural Networks

Part of the book series: NATO ASI Series ((NATO ASI F,volume 136))

  • 367 Accesses

Abstract

Multilayer perceptrons generate a posteriori probabilities related to emission probabilities of Hidden Markov Models through Bayes rule. This property is used to improve the discrimination of H M M. Moreover, it gives rise to many statistical interpretations which can be cast in neural architectures for nonlinear prediction and triphone probability estimation.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. F. Jelinek, Continuous Recognition by Statistical Methods, Proceedings IEEE, vol. 64 no 4, pp.532–555, 1976.

    Article  Google Scholar 

  2. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K. Lang, Phoneme Recognition: Neural Networks vs. Hidden Markov Models, Proc. Intl. Conf. on Acoustics, Speech and Signal Processing, New York, vol.1, pp107–110, 1988.

    Google Scholar 

  3. H. Bourlard & C.J. Wellekens, Multilayer Perceptrons and Speech Recognition, IEEE Proc. of the First International Conf. on Neural Networks, vol IV, pp.407–416, San Diego, CA, 1987.

    Google Scholar 

  4. H. Bourlard & C.J. Wellekens, Links between Markov Models and Multilayer Perceptrons, Computer, Speech and Language, vol.3, pp. 1–19, 1989

    Article  Google Scholar 

  5. R.P. Lippmann, Neural Network Classifiers Estimate Bayesian a Posteriori Probabilities, Neural Computation, vol.3, no 4, pp. 461–484, 1991.

    Article  Google Scholar 

  6. R.P. Lippmann, An Introduction to Computing with Neural Nets, IEEE Acoustic, Speech, and Signal Processing Magazine, vol. 4, no 2, pp.4–22, 1987.

    Google Scholar 

  7. M. Cohen, H. Franco, N. Morgan, D.E. Rumelhart & V. Abrash, Hybrid Neural Network/Hidden Markov Model Continuous Speech Recognition, Proc. Intl. Conf. on Spoken Language Processing, vol2, pp. 915–918, Banff, Canada, 1992.

    Google Scholar 

  8. H. Bourlard, Continuous Speech Recognition: From Hidden Markov Models to Artificial Neural Networks, Doctoral Dissertation, Faculté Polytechnique de Mons, Belgium, Feb.1992.

    Google Scholar 

  9. H. Bourlard, N. Morgan, Chuck Wooters & Steve Renais, CDNN: A Context Dependent Neural Network for Continuous Speech Recognition, IEEE Proc. Intl. Conf. on Acoustics, Speech and Signal Processing San Francisco, CA, vol.2 pp. 349–352, 1992.

    Google Scholar 

  10. C.J. Wellekens, Explicit Time Correlation in Hidden Markov Models in Speech Recognition, Proc. IEEE Conference on Audio, Speech and Signal Processing, pp.384–387, April 1987.

    Google Scholar 

  11. E. Levin, Speech Recognition Using Hidden Control Neural Network Architecture, IEEE Proc. Intl. Conf. on Acoustics, Speech, and Signal Processing, pp. 433–436, Albuquerque, NM, 1990.

    Google Scholar 

  12. S. Furui, Speaker Independent Isolated Word Recognizer Using Dynamic Features of Speech Spectrum, IEEE Trans. on Acoustic, Speech, ans Signal Processing, vol.34, no 1, pp 52–59, 1986.

    Article  Google Scholar 

  13. M. Minsky & S. Papert, Perceptrons, Cambridge, MA: MIT Press, 1969.

    MATH  Google Scholar 

  14. D.E. Rumelhart, G.E. Hinton & R.J. Williams, Parallel Distributed Processing. Exploration of the Microstructure of Cognition, vol.1: Foundations, Ed. D.E. Rumelhart & J.L. McClelland, MIT Press, 1986.

    Google Scholar 

  15. N. Morgan & H. Bourlard, Continuous Speech Recognition Using Multilayer Perceptrons with Hidden Markov Models, IEEE Intl. Conf. on Audio, Speech and Signal Processing, pp. 413–416, Albuquerque, New Mexico, 1990.

    Google Scholar 

  16. N. Morgan, J. Beck, P. Kohn, J. Bilmes, E. Allman & J. Beer, The Ring Array Processor (RAP): A multiprocessing peripheral for connectionist applications, Journal of Parallel and Distributed Computing, 1992.

    Google Scholar 

  17. L.R. Rabiner, B.H. Juang, “Fundamentals of Speech Recognition”, Prentice Hall, 1993.

    Google Scholar 

  18. L.R. Rabiner, R.W. Schafer, “Digital Processing of Speech Signals”, Prentice Hall, 1978.

    Google Scholar 

  19. J.R. Deller, J.G. Proakis, J.H. L.Hansen,”Discrete-Time Processing of Speech Signals”, Mc Millan, 1993.

    Google Scholar 

  20. H. Hermansky, Perceptual Linear Predictive (PLP) Analysis of Speech, Jl of Acoustical Soc. of America, vol 87, no 4.

    Google Scholar 

  21. H.Hermansky, J-C Junqua, Optimization of Perceptually-Based ASR Front-End, ICASSP 88, pp. 219–222.

    Google Scholar 

  22. Y. Linde, A. Buzo, R.M. Gray, An Algorithm for Vector Quantizer Design, IEEE Trans. on Communications, vol 28, no 1, pp. 84–95, 1980.

    Article  Google Scholar 

  23. H. Ney, The Use of One-Stage Dynamic Programming Algorithm for Connected Word Recognition, IEEE Trans. on Acoustic, Speech and Signal Processing, pp 833–836. (1984)

    Google Scholar 

  24. J.S. Bridie, M.D. Brown, R.M. Chamberlain, An Algorithm for Connected Word Recognition, ICASSP 1982, pp.899–902.

    Google Scholar 

  25. H. Bourlard, C.J. Wellekens, Links between Markov Models and Multilayer Perceptrons, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol 12, no 12, pp. 1167–1178.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institut EURECOM, 06904, Sophia Antipolis, France

    Chris J. Wellekens

Authors
  1. Chris J. Wellekens
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Electrical Engineering, University of Minnesota, Minneapolis, MN, 55455, USA

    Vladimir Cherkassky

  2. Department of Statistics, Stanford University, Stanford, CA, 94309, USA

    Jerome H. Friedman

  3. Computer Science Department, George Mason University, Fairfax, VA, 22030, USA

    Harry Wechsler

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Wellekens, C.J. (1994). Improved Hidden Markov Models for Speech Recognition Through Neural Network Learning. In: Cherkassky, V., Friedman, J.H., Wechsler, H. (eds) From Statistics to Neural Networks. NATO ASI Series, vol 136. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79119-2_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-79119-2_11

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-79121-5

  • Online ISBN: 978-3-642-79119-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation