Speech Recognition Based on Pattern Recognition Approaches

  • Lawrence R. Rabiner
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 155)


Algorithms for speech recognition can be characterized broadly as pattern recognition approaches and acoustic phonetic approaches. To date, the greatest degree of success in speech recognition has been obtained using pattern recognition paradigms. Thus, in this paper, we will be concerned primarily with showing how pattern recognition techniques have been applied to the problems of isolated word (or discrete utterance) recognition, connected word recognition, and continuous speech recognition. We will show that our understanding (and consequently the resulting recognizer performance) is best for the simplest recognition tasks and is considerably less well developed for large scale recognition systems.


Word Recognition Speech Recognition Speech Signal Dynamic Time Warping Reference Pattern 
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]
    N. R. Dixon and T. B. Martin, Eds., Automatic Speech and Speaker Recognition, New York: IEEE Press, 1979.Google Scholar
  2. [2]
    W. Lea, Ed., Trends in Speech Recognition, Englewood Cliffs, NJ: Prentice-Hall, 1980.Google Scholar
  3. [3]
    G. R. Doddington and T. B. Schalk, “Speech Recognition: Turning Theory into Practice,” IEEE Spectrum, Vol. 18, No. 9, pp. 26–32, Sept. 1981.Google Scholar
  4. [4]
    L. R. Bahl, F. Jelinek, and R. L. Mercer, “A Maximum Likelihood Approach to Continuous Speech Recognition,” IEEE Trans, on Pattern Analysis and Machine Intelligence, Vol. PAMI-5, No. 2, pp. 179–190, March 1983.CrossRefGoogle Scholar
  5. [5]
    A. E. Rosenberg, L. R. Rabiner, J. G. Wilpon, and D. Kahn, “Demisyllable-Based Isolated Word Recognition,” IEEE Trans, on Acoustics, Speech, and Signal Processing, Vol. ASSP-31, No. 3, pp. 713–726, June 1983.CrossRefGoogle Scholar
  6. [6]
    F. Itakura, “Minimum Prediction Residual Principle Applied to Speech Recognition,” IEEE Trans, on Acoustics, Speech, and Signal Processing, Vol. ASSP-23, pp. 67–72, Feb. 1975.CrossRefGoogle Scholar
  7. [7]
    F. Jelinek, “Speech Recognition by Statistical Methods,” Proc. IEEE, Vol. 65, pp. 532–556, April 1976.CrossRefGoogle Scholar
  8. [8]
    S. E. Levinson, L. R. Rabiner, and M. M. Sondhi, “An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition,” Bell System Tech. Jour., Vol. 62, No. 4, pp. 1035–1074, April 1983.MathSciNetzbMATHGoogle Scholar
  9. [9]
    B. A. Dautrich, L. R. Rabiner, and T. B. Martin, “On the Effects of Varying Filter Bank Parameters on Isolated Word Recognition,” IEEE Trans, on Acoustics, Speech, and Signal Processing, Vol. ASSP-31, No. 4, pp. 793–807, Aug. 1983.CrossRefGoogle Scholar
  10. [10]
    L. D. Markel and A. H. Gray, Jr., Linear Prediction of Speech, New York: Springer-Verlag, 1976.zbMATHCrossRefGoogle Scholar
  11. [11]
    H. Sakoe, “Two Level DP Matching — A Dynamic Programming Based Pattern Matching Algorithm for Connected Word Recognition,” IEEE Trans, on Acoustics, Speech, and Signal Processing, Vol. ASSP-27, pp. 588–595, Dec. 1979.CrossRefGoogle Scholar
  12. [12]
    C. S. Myers and L. R. Rabiner, “Connected Digit Recognition Using a Level Building DTW Algorithm,” IEEE Trans, on Acoustics, Speech, and Signal Processing, Vol. ASSP-29, No. 3, pp. 351–363, June 1981.CrossRefGoogle Scholar
  13. [13]
    J. S. Bridle, M. D. Brown, and R. M. Chamberlain, “An Algorithm for Connected Word Recognition,” Automatic Speech Analysis and Recognition, J. P. Haton, Ed., pp. 191-204, 1982.Google Scholar
  14. [14]
    J. L. Gauvain and J. Mariani, “A Method for Connected Word Recognition and Word Spotting on a Microprocessor,” Proc. 1982 ICASSP, pp. 891-894, May 1982.Google Scholar
  15. [15]
    L. R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,” Proc. IEEE, Vol.77, No. 2, pp. 257–286, Feb. 1989.CrossRefGoogle Scholar
  16. [16]
    F. Jelinek, “The Development of an Experimental Discrete Dictation Recognizer,” Proc. IEEE, Vol.73, No. 11, pp. 1616–1624, Nov. 1985.CrossRefGoogle Scholar
  17. [17]
    K. F. Lee, H. W. Hon, and D. R. Reddy, “An Overview of the SPHINX Speech Recognition System,” IEEE Trans, on Acoustics, Speech, and Signal Proc., Vol. 38, pp. 600–610, 1990.Google Scholar
  18. [18]
    Y. L. Chow, M. O. Dunham, O. A. Kimball, M. A. Krasner, G. F. Kubala, J. Makhoul, S. Roucos, and R. M. Schwartz, “BBYLOS: The BBN Continuous Speech Recognition System,” Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Proc., pp. 89-92, Apr. 1987.Google Scholar
  19. [19]
    D. B. Paul, “The Lincoln Robust Continuous Speech Recognizer,” Proc. ICASSP 89, Glasgow, Scotland, pp. 449-452, May 1989.Google Scholar
  20. [20]
    M. Weintraub et al., “Linguistic Constraints in Hidden Markov Model Based Speech Recognition,” Proc. ICASSP 89, Glasgow, Scotland, pp. 699-702, May 1989.Google Scholar
  21. [21]
    V. Zue, J. Glass, M. Phillips, and S. Seneff, “The MIT Summit Speech Recognition System: A Progress Report,” Proc. Speech and Natural Language Workshop, pp. 179-189, Feb. 1989.Google Scholar
  22. [22]
    C. H. Lee, L. R. Rabiner, R. Pieraccini, and J. G. Wilpon, “Acoustic Modeling for Large Vocabulary Speech Recognition,” Computer Speech and Language, Vol. 4, pp. 127–165, 1990.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1992

Authors and Affiliations

  • Lawrence R. Rabiner
    • 1
  1. 1.Information Principles ResearchAT&T Bell LaboratoriesMurray HillUSA

Personalised recommendations