Advertisement

Processing Self-Corrections in a Speech-to-Speech System

  • Jörg Spilker
  • Martin Klarner
  • Günther Görz
Part of the Artificial Intelligence book series (AI)

Abstract

Self-repairs are a frequent phenomenon in spontaneous speech. The ability to detect and correct those repairs is therefore indispensable for any spoken language system. We present a framework for detection and correction of speech repairs where all relevant levels of information, i.e., acoustics, lexis, syntax and semantics can be integrated. The basic idea is to reduce the search space for repairs as soon as possible by cascading filters that involve more and more features. At first an acoustic module generates hypotheses about the existence of a repair. Afterwards a stochastic model suggests a correction for every hypothesis. Hihgly scored corrections are inserted as new paths in the word lattice. Finally, a lattice parser decides wether the repair should be accepted or not.

Keywords

Interruption Point Statistical Machine Translation Spontaneous Speech Word Fragment Speech Recognizer 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Batliner, A., Buckow, J., Niemann, H., Nöth, E., and Warnke, V. The Prosody Module. In this volume. Google Scholar
  2. Bear, J., Dowding, J., and Shriberg, E. (1992). Integrating Multiple Knowledge Sources for Detection and Correction of Repairs in Human Computer Dialogs. In Proceedings of the ACL, 56–63.Google Scholar
  3. Brown, P.F., Cocke, J., Della Pietra, S.A., Della Pietra, V.J., Jelinek, F., Lafferty, J.D., Mercer, R.L., and Roossin, P.S. (1990). A Statistical Approach to Machine Translation. Computational Linguistics 16(2):79–85.Google Scholar
  4. Brown, P.F., Della Pietra, S.A., Della Pietra, V.J., and Mercer, R.L. (1993). The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics 19(2):263–311.Google Scholar
  5. Core, M.G., and Schubert, K. (1999). Speech Repairs: A Parsing Perspective. Satellite meeting ICPHS 99.Google Scholar
  6. Dowing, J., Gawron, J.M., Appelt, D., Bear, J., Cherny, L., Moore, R., and Moran, D. (1993). Gemini: a Natural Language System for Spoken-Langugae Understanding. In Proceedings of the ACL, 54–61.Google Scholar
  7. Heeman, P.A., and Allen, J.F. (1999). Speech Repairs, Intonational Phrases, and Discourse Markers: Modelling Speakers’ Utterances in Spoken Dialogue. Computational Linguistics 25(4):527–571.Google Scholar
  8. Hindle, D. (1983). Deterministic Parsing of Syntactic Nonfluencies. In Proceedings of the ACL. Google Scholar
  9. Katz, S.M. (1987). Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recognizer. Transaction on Acoustics, Speech and Signal Processing ASSP-35.Google Scholar
  10. Klakow, D., Rose, G., and Aubert, X. (1999). OOV- Detection in Large Vocabulary System Using Automatically Defined Word-Fragments as Fillers. In Proceedings of the EUROSPEECH ’99, volume 1, 49–52.Google Scholar
  11. Levelt, W. (1983). Monitoring and Self-Repair in Speech. Cognition 14:41–104.CrossRefGoogle Scholar
  12. Nakatani, C., and Hirschberg, J. (1993). A Speech-First Model for Repair Detection and Correction. In Proceedings of the ACL. Google Scholar
  13. Samuelsson, C. (1997). A Left-to-Right Tagger for Word Graphs. In Proceedings of the 5th International workshop on Parsing technologies, 171–178.Google Scholar
  14. Stolcke, A., Shriberg, E., Hakkani-Tur, D., and Tur, G. (1999). Modeling the Prosody of Hidden Events for Improved Word Recognition. In Proceedings of the EUROSPEECH ’99, volume 1, 307–310.Google Scholar
  15. Tessiore, L., and v. Hahn, W. Functional Validation of a Machine Interpretation System: Verbmobil. In this volume. Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Jörg Spilker
    • 1
  • Martin Klarner
    • 1
  • Günther Görz
    • 1
  1. 1.Department of Computer ScienceUniversität Erlangen-NürnbergGermany

Personalised recommendations