Layering Predictions: Flexible Use of Dialog Expectation in Speech Recognition
نویسندگان
چکیده
ion Spaces". Artificial Intelligence 5, 2 (1974),8. Fink, P. K. and Biermann, A. W. "The Correction of 115-135.Ill-Formed Input Using History-Based Expectation WithApplications to Speech Understanding". Computational 22. Searle, J. R. Indirect Speech Acts. In Syntax and Linguistics 12 (1986), 13-36.Semantics, Volume 3: Speech Acts, New York: Academic Press, 1975.9. Gatward, R.A., Johnson, S.R. and Conolly, J.H. ANatural Language Processing System Based on Functional 23. Walker, D.E. SRI Research on Speech Understanding. Grammar. Speech Input/Output; Techniques andIn Lea, W.A., Ed., Trends in Speech Recognition, PrenticeApplications, Institute for Electrical Engineers, 1986, pp. Hall, Englewood Cliffs, NJ, 1980, pp. 294 315. 125 128.24. Wilensky, R. Understanding Goal-Based Stories.10. Grosz, B. J. and Sidner, C. L. "Attention, Intentions Ph.D. Th., Yale University, Sept. 1978. and the Structure of Discourse". Computation Linguistics25. Wilensky, R. Planning and Understanding. Addison12 (1986), 175-204.Wesley, Reading, MA, 1983.11. Hauptmann, A. G., Young, S. R. and Ward, W. H.26. Woods, W.A., Bates, M., Brown, G., Bruce, B., Cook,Using Dialog Level Knowledge Sources to Improve SpeechC., Klovstad, J., Makhoul, J., Nash-Webber, B., Schwartz,Recognition. Proceedings of the Seventh NationalR., Wolf, J., and Zue, V. Speech Understanding Systems -Conference on Artificial Intelligence, 1988.Final Technical Report. Tech. Rept. 3438, Bolt, Beranek,12. Hayes, P.J., Hauptmann, A.G., Carbonell, J.G. and and Newman, Inc., Cambridge, MA, 1976. Tomita, M. Parsing Spoken Language: a Semantic27. Young, S. R. and Ward, W. H. Towards HabitableCaseframe Approach. Proceedings of COLING-86,Systems: Use of World Knowledge to DynamicallyAssociation for Computational Linguistics, Bonn, Germany,Constrain Speech Recognition. The Second Symposium onAugust, 1986.Advanced Man Machine Interface Through Spoken13. Kimball, O., Price, P., Roucos, S., Schwartz, R.,Language, 1988.Kubala, F., Chow, Y.-L., Haas, A., Krasner, M. and28. Young, S. R., Hauptmann, A. G., Ward, W. H., Smith,Makhoul, J. Recognition Performance and GrammaticalE. T. and Werner, P. "High Level Knowledge Sources inConstraints. Proceedings of the DARPA SpeechUsable Speech Recognition Systems". Communications ofRecognition Workshop, Science Applications Internationalthe ACM 32, 2 (1989), .Corporation Report Number SAIC-86/1546, 1986, pp. 53 -59. 14. Lea, W.A. (Ed.) Trends in Speech Recognition.Prentice-Hall, Englewood Cliffs, NJ, 1980. 15. Lee, K. SPHINX: Large Vocabulary, Speaker-Independent Speech Recognition. Ph.D. Th., Carnegie-Mellon University, 1988. Table of
منابع مشابه
A flexible and integrated interface between speech recognition, speech interpretation and dialog management
This paper presents an integrated interface between speech recognition, speech interpretation and dialog control intended for spoken dialog systems coping with natural speech input. During the system design phase the interface co-ordinates corpus acquisition and annotation, grammar development and the construction of stochastic hierarchical language models. During system runtime, it links toget...
متن کاملFlexible Speech Act Based Dialogue Management
We present an application independent dialogue engine that reasons on application dependent knowledge sources to calculate predictions about how a dialogue might continue. Predictions are language independent and are translated into language dependent structures for recognition and synthesis. Further, we discuss how the predictions account for di erent kinds of dialogue, e.g., question-answer o...
متن کاملA spoken dialog system for a mobile office robot
A spoken dialog interface of a mobile office robot is described. To realize robust speech recognition in noisy office environments, a microphone array system and a technique of switching multiple speech recognition processes with different dictionaries are introduced. To realize flexible and natural dialog, task dependent semantic frames and keeping track of attentional state of dialog are used...
متن کاملA Flexible and Integrated Interface be Speech Interpretation and Di
This paper presents an integrated interface between speech recognition, speech interpretation and dialog control intended for spoken dialog systems coping with natural speech input. During the system design phase the interface co-ordinates corpus acquisition and annotation, grammar development and the construction of stochastic hierarchical language models. During system runtime, it links toget...
متن کاملBackoff Model Training using Partially Observed Data: Application to Dialog Act Tagging
Dialog act (DA) tags are useful for many applications in natural language processing and automatic speech recognition. In this work, we introduce hidden backoff models (HBMs) where a large generalized backoff model is trained, using an embedded expectation-maximization (EM) procedure, on data that is partially observed. We use HBMs as word models conditioned on both DAs and (hidden) DAsegments....
متن کامل