Speech Recognition Based on Pattern Recognition Approaches
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.
KeywordsWord Recognition Speech Recognition Speech Signal Dynamic Time Warping Reference Pattern
Unable to display preview. Download preview PDF.
- N. R. Dixon and T. B. Martin, Eds., Automatic Speech and Speaker Recognition, New York: IEEE Press, 1979.Google Scholar
- W. Lea, Ed., Trends in Speech Recognition, Englewood Cliffs, NJ: Prentice-Hall, 1980.Google Scholar
- 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
- 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
- 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
- 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
- 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
- D. B. Paul, “The Lincoln Robust Continuous Speech Recognizer,” Proc. ICASSP 89, Glasgow, Scotland, pp. 449-452, May 1989.Google Scholar
- 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
- 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