Control of Syntax and Semantics in Continuous Speech Understanding

  • W. A. Woods
Part of the NATO Advanced Study Institutes Series book series (ASIC, volume 59)

Abstract

A naive view of speech understanding might consider it as a process of successively recognizing speech sounds (called phonemes), grouping phonemes into words, parsing word sequences into sentences, and finally interpreting the meanings of those sentences. However, considerable experience now indicates that the acoustic evidence present in the original speech signal is not sufficient to support such a process [Woods and Makhoul, 1974]. For sentences recorded from continuous speech, it is not generally possible to reliably determine the phonetic identity of the individual phonemes (or even to be sure how many phonemes are present) using the acoustic evidence alone. Experiments in spectrogram reading [Klatt and Stevens, 1971] indicate that the reliability of such determinations can be increased by use of the redundancy provided by knowledge of the vocabulary, the syntax of the language, and semantic and pragmatic considerations.

Keywords

Helium Ghost Acoustics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bahl, L.R., Baker, J.K., Cohen, P.S., Cole, A.G., Jelinek, F., Lewis, B.L., and Mercer, R.L. (1978) “Automatic Recognition of Continuously Spoken Sentences from a Finite State Grammar.” Conference Record, 1978 IEEE Int’l Conf, on Acoustics, Speech and Signal Processing, Tulsa, OK, April, 1978, IEEE 78CH1285-6 ASSP.Google Scholar
  2. Bahl, L.R., Baker, J.K., Cohen, P.S., Dixon, N.R., Jelinek, F., Mercer, R.L., and Silverman, H.F. (1976) “Preliminary Results on the Performance of a System for the Automatic Recognition of Continuous Speech,” Conference Record, IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, ICASSP-76, Philadelphia, Pa., April, 1976.Google Scholar
  3. Baker, J.K. (1975) “The DRAGON System — An Overview,” IEEE Trans. Acoustics, Speech and Signal Processing, February, Vol. ASSP-23, No. 1, pp. 24–29.CrossRefGoogle Scholar
  4. Chomsky, N. (1965) Aspects of the Theory of Syntax. Cambridge, MA: MIT Press.Google Scholar
  5. Hayes-Roth, F, and Lesser, V.R. (1976) “Focus of Attention in a Distributed-Logic Speech Understanding System,” Conference Record, IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP-76, Philadelphia, Pa., April, 1976.Google Scholar
  6. Klatt, D.H. and Stevens, K.N. (1971) “Strategies for Recognition of Spoken Sentences from Visual Examination of Spectrograms,” BBN Report No. 2154, Bolt Beranek and Newman Inc., Cambridge, MA.Google Scholar
  7. Lesser, V.R., Fennell, R.D., Erman, L.D., and Reddy, D.R. (1975) “Organization of the Hearsay II Speech Understanding System,” IEEE Trans. Acoustics, Speech, and Signal Processing, February, Vol. ASSP-23, No. 1, pp. 11–24.CrossRefGoogle Scholar
  8. Lowerre, Bruce T. (1976) “The HARPY Speech Recognition System,” Technical Report, Department of Computer Science, Carnegie-Mellon Univ., April, 1976.Google Scholar
  9. Nash-Webber, B.L. (1975) “The Role of Semantics in Automatic Speech Understanding.” In Representation and Understanding: Studies in Cognitive Science, D. Bobrow and A. Collins (eds.), New York: Academic Press.Google Scholar
  10. Newell, A. et al. (1973) Speech Understanding Systems: Final Report of a Study Group, Amsterdam: North Holland/American Elsevier.Google Scholar
  11. Paxton, W.H.. (1977) “A Framework for Speech Understanding,” Stanford Research Institute Artificial Intelligence Center, Technical Note 142, June 1977.Google Scholar
  12. Wanner, E. (1973) “Do We Understand Sentences from the Outside-in or from the Inside-out?,” Daedalus, pp. 163–183, Summer.Google Scholar
  13. Wolf, J.J. and W.A. Woods (1977) “The HWIM Speech Understanding System,” Conference Record, IEEE International Conference on Acoustics, Speech and Signal Processing, Hartford, Conn., May, 1977.Google Scholar
  14. Woods, W.A. and Makhoul, J.I. (1974) “Mechanical Inference Problems in Continuous Speech Understanding.” In Artificial Intelligence, Vol. 5, No. 1, pp. 73–91.Google Scholar
  15. Woods, W., M. Bates, G. Brown, B. Bruce, C. Cook, J. Klovstad, J. Makhoul, B. Nash-Webber, R. Schwartz, J. Wolf, V. Zue (1976) “Speech Understanding Systems — Final Technical Progress Report,” BBN Report No. 3438 Vols. I–V, Bolt Beranek and Newman Inc., Cambridge, Ma.Google Scholar
  16. Woods, W.A. (1970) “Transition Network Grammars for Natural Language Analysis,” Communications of the ACM, Vol. 13, No. 10, October, 1970, pp. 591–606.Google Scholar
  17. Woods, W.A. (1975) “Syntax, Semantics, and Speech,” in D.R. Reddy (ed.), Speech Recognition: Invited Papers at the IEEE Symposium, New York: Academic Press. (Also as BBN Report No. 3067).Google Scholar
  18. Woods, W.A. (1977) “Theory Formation and Control in a Speech Understanding System with Extrapolations towards Vision,” Proc. of Workshop on Computer Vision Systems, University of Massachusetts, Amherst, June.Google Scholar
  19. Woods, W.A. (1978a) “Semantics and Quantification in Natural Language Question Answering.” In Advances in Computers, Vol. 17. New York: Academic Press.Google Scholar
  20. Woods, W.A. (1978b) “Generalizations of ATN Grammars,” in Woods & Brachman, Research in Natural Language Understanding, BBN Report No. 3963, August.Google Scholar

Copyright information

© D. Reidel Publishing Company 1980

Authors and Affiliations

  • W. A. Woods
    • 1
  1. 1.Bolt Beranek and Newman Inc.CambridgeUSA

Personalised recommendations