Computer as a research tool in speech-understanding systems research

  • D. Raj Reddy
Part of the FASEB Monographs book series (FASEBM, volume 2)


Speech-Understanding Systems (2), likeseveral other problems that arise in Artificial Intelligence research, are characterized by high data rates, large amounts of data, and the need to perceive, understand and respond in real time. Thus, while it is acceptable to take 3–5 min to respond to a chess move, one expects an immediate response during a conversation. Unlike the conventional scientific applications, where the solution is known and merely needs to be programmed, in this case not only are the solutions not known but even the research methodology for the discovery of a solution was not well understood a few years ago. Thus the computer plays an important role in the scientific discovery for formulation and validation of models that can explain the perceptual phenomena associated with speech understanding. The role of such an interactive computer research system in information processing psychology is analogous to the role of an electron microscope in neurobiology. In this paper we will briefly discuss the structure and organization of a working speech-understanding system and discuss the facilities in our research environment and their relevance to this research.


High Data Rate Research Computer Speech Understanding Computer Science Research Display Processor 
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.
    Miller, G. A., and S. Isard. Some perceptual consequences of linguistic rules. J. Verbal Learning Behav. 2: 217–228, 1963.CrossRefGoogle Scholar
  2. 2.
    Newell, A, J. Barnett, J. Forgie, C. Green, D. Klatt, J. C. R. Licklider, J. Munson, R. Reddy and W. Woods. Final report of a study group on speech understanding systems. (First published in report form, 1971). Amsterdam: North-Holland, 1973.Google Scholar
  3. 3.
    Reddy, D. R. Some numerical problems in artificial intelligence: implications for complexity and machine architecture. In: Complexity of Sequential and Parallel Numerical Algorithms, edited by J. F. Traub, New York: Academic, 1973, p. 131–147.Google Scholar
  4. 4.
    Reddy, D. R., W. J. Davis, R. B. Ohlander and D. Bihary. Computer analysis of neuronal structure. In: Intracellular Staining Techniques In Neurobiology, edited by S. B. Kater and C. Nicholson. New York: Springer-Verlag, 1973, 227–254.CrossRefGoogle Scholar
  5. 5.
    Reddy, D. R., L. D. Erman, R. D. Fennell and R. B. Neely. The Hearsay speech understanding system: an example of the recognition process. 3rd. Intern. Joint Conf. Artificial Intelligence. Stanford, Calif. 1973, p. 185-193.Google Scholar
  6. 6.
    Reddy, D. R., L. D. Erman and R. B. Neely. A model and a system for machine recognition of speech. IEEE Trans. Audio Electroacous-tics, AU-21 (3): 229–238, 1973.CrossRefGoogle Scholar
  7. 7.
    Reddy, D. R., and A. Newell. Knowledge and its representation in a speech understanding system. In: Knowledge and Cognition, edited by L. W. Gregg, Washington, D. C: Lawrence Erlbaum Assoc, In press.Google Scholar
  8. 8.
    Shannon, D. E. Prediction and entropy of printed English. Bell System Tech. J. 30: 50–64, 1951.CrossRefGoogle Scholar
  9. 9.
    Wulf, W. A., and C. G. Bell. C. mmp: A multi-mini-processor. Proc. Fall Joint Computer Conf. 1972, p. 765-778.Google Scholar

Copyright information

© Springer Science+Business Media New York 1974

Authors and Affiliations

  • D. Raj Reddy
    • 1
  1. 1.Carnegie-Mellon UniversityPittsburghUSA

Personalised recommendations