Advertisement

Adaptive Networks and Speech Pattern Processing

  • John S. Bridle
Conference paper
Part of the NATO ASI Series book series (volume 30)

Abstract

This is an introduction to and interpretation of some techniques which have been developed recently for pattern processing. The first part is concerned with the stochastic modelling approach to pattern recognition, which includes structural and statistical aspects. Various varieties of hidden Markov models, which are the basis of the most successful current automatic speech recognition systems, are viewed as a special case of Markov random fields. The second part is concerned with adaptive networks which “learn” to do jobs such as pattern classification, without necessarily containing explicit models of the data distributions. The main approaches covered are the Boltzmann machine (which is also interpreted as a Markov random field) and a recently invented multi-layer perceptron network.

Keywords

Hide Markov Model Speech Recognition Gibbs Sampler Markov Random Field State Transition Matrix 
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]
    J. Makhoul and R. Schwartz, “Ignorance modelling,” in J. Perkell and D. Klatt eds., Invariance and Variability in Speech Processes, Erlbaum, 1986, pp. 344–345.Google Scholar
  2. [2]
    D.R. Cox and H.D. Millar, The Theory of Stochastic Processes, Methuen, 1965.MATHGoogle Scholar
  3. [3]
    S. Geman and D. Geman, “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,” IEEE Trans, on Pattern Analysis and Machine Intelligence, vol. PAMI-6, no.6, November 1984, pp. 721–741.Google Scholar
  4. [4]
    T. Poggio et al;., “Computational vision and regularization theory,” Nature, Vol. 317, 26, Sept. 1985.Google Scholar
  5. [5]
    M.R. Russell and R.K. Moore, “Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition,” IEEE ICASSP-85. Google Scholar
  6. [6]
    S.E. Levinson, “A Unified theory of composite pattern analysis for automatic speech recognition,” in F. Fallside and W. Woods eds., Computer Speech Processing, Prentice Hall, 1984.Google Scholar
  7. [7]
    J.K.Baker, “Trainable grammars for speech recognition,” Speech communication papers for the 97th meeting of the Acoust. Soc. Amer., D.H.Klatt & J.J.Wolf eds. 1979, pp. 547–550.Google Scholar
  8. [8]
    J.S. Bridie, “Pattern recognition techniques for speech recognition,” in Spoken Language Generation and Understanding, NATO ASI Series, Reidel, pp. 129–145.Google Scholar
  9. [9]
    M. Minsky and S. Papert, Perceptrons: An Introduction to Computational Geometry, M.I.T. Press, 1969.MATHGoogle Scholar
  10. [10]
    D.E. Rummelhart, G.E. Hinton and R.J. Williams, “Learning internal representations by error propagation,” ICS Report 8506, University of California, San Diego, Sept. 1985.Google Scholar
  11. [11]
    G.E. Hinton, T.J. Sejnowski and D.H. Ackley, “Boltzmann machines: constraint satisfaction networks that learn,” Technical Report CMU-CS-84–119, Carnegie-Mellon University, May 1984.Google Scholar
  12. [12]
    D.H. Ackley, G.E. Hinton and T.J. Sejnowski, “A learning algorithm for Boltzmann machines,” Cognitive Science, 9, 1985, pp. 147–168.CrossRefGoogle Scholar
  13. [13]
    G.E. Hinton, “Learning in parallel networks,” BYTE, April 1985, pp. 265–273.Google Scholar
  14. [14]
    J.S. Bridie and R.K. Moore, “Boltzman machines for speech pattern processing,” Proc. Inst Acoust., Nov. 1984, pp. 1–8.Google Scholar
  15. [15]
    G.E. Hinton and T.J. Sejnowski, “Optimal perceptual inference,” Proc. IEEE Computer Soc. Conf. on Computer Vision and Pattern Recognition, Washington, D.C., June 1983, pp. 448–453.Google Scholar
  16. [16]
    G. Hinton, “Distributed representations,” Dept. Computer Science, Carnegie-Mellon University, Pittsburgh, Oct. 1984.Google Scholar
  17. [17]
    J.A. Feldman, “Energy and behavior in connectionist models,” Rochester U., CS Tech. Rep. TR155, Nov.1985.Google Scholar
  18. [18]
    T.J. Seinowski, and C.R. Rosenberg, “NETtalk: A parallel network that learns to read aloud,” Johns Hopkins U., EE&CS Tech. Rep. JHU/EECS-86/01, 1986.Google Scholar
  19. [19]
    J.F.Traherneet ah, “Speech processing with a Boltzmann machine,” IEEE ICASSP-86, Tokyo, pp. 725–728.Google Scholar
  20. [20]
    R.G. Prager et al, “Boltzmann machines for speech recognition,” Computer Speech and Language, Vol.1, No.l, 1986.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1987

Authors and Affiliations

  • John S. Bridle
    • 1
  1. 1.Speech Research UnitRoyal Signals and Radar EstablishmentMalvernEngland

Personalised recommendations