Abstract
Human speech understanding works incrementally. We begin to process acoustic input before the speaker’s utterance has ended. A system capable of performing sophisticated communication in a natural dialogue or simultaneous interpreting, has to work incrementally, too. The architecture of such a system should be modular, uniform and integrated. We present an architectural framework that suits these three requirements by implementing layered charts, a multi-purpose data structure intended to represent several competing hypotheses about linguistic content of utterance intervals based on hyper graphs. We demonstrate the feasibility by presenting results from an actual interpreting system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Steven Abney. Partial Parsing via Finite-State Cascades. In Proceedings of the ESSLLI ’96 Robust Parsing Workshop, 1996.
Jan Alexandersson, Norbert Reithinger, and Elisabeth Maier. Insights into the Dialogue Processing of Verbmobil. In Proc. of the 5th Conference on Applied Natural Language Processing, Washington, D.C., 1997.
Jan W. Amtrup. ICE: A Communication Environment for Natural Language Processing. In Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA97), Las Vegas, NV, July 1997.
Jan W. Amtrup. Layered Charts for Speech Translation. In Proceedings of the Seventh International Conference on Theoretical and Methodological Issues in Machine Translation, TMI ’97, Santa Fe, NM, July 1997.
Jan W. Amtrup. Perspectives for Incremental MT with Charts. In Christa Hauenschild and Susanne Heizmann, editors, Machine Translation and Translation Theory. Perspectives of Cooperation, Text, Translation, Computational Processing (TTCP), number 1. Mouton de Gruyter, 1997.
Jan W. Amtrup and Volker Weber. Time Mapping with Hypergraphs. In Proc. of the 17 th COLING, Montreal, Canada, 1998.
Xavier Aubert and Hermann Ney. Large Vocabulary Continuous Speech Recognition Using Word Graphs. In ICASSP 95, 1995.
Christian Boitet and Mark Seligman. The “Whiteboard” Architecture: A Way to Integrate Heterogeneous Components of NLP systems. In COLING-94: The 15th International Conference on Computational Linguistics, Kyoto, Japan, 1994.
Thomas Bub, Wolfgang Wahlster, and Alex Waibel. Verbmobil: The Combination of Deep and Shallow Processing for Spontaneous Speech Translation. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, pages 1/7a1–1/74, Munich, Germany, 1997.
Bob Carpenter. The Logic of Typed Feature Structures. Tracts in Theoretical Computer Science. Cambridge University Press, Cambridge, 1992.
David Carter et al. Translation Methodology in the Spoken Language Translator: An Evaluation. In ACL Workshop on Spoken Language Translation, 1997.
G. V. Chernov. Message redundancy and message anticipation in simultaneous interpretation. In Lambert and Moser-Mercer, editors, Bridging the Gap: Empirical Research in Simultaneous Interpretation, pages 139–153. John Benjamins, 1994.
Michael Finke, Maria Lapata, Alon Lavie, Lori Levin, Laura Mayfield Tomokiyo, Thomas Polzin, Klaus Ries, Alex Waibel, and Klaus Zechner. Clarity: Inferring Discourse Structure from Speech. In Proceedings of the AAAI 98 Spring Symposium: Applying Machine Learning to Discourse Processing, pages 23–32, Stanford, CA, 1998.
Wolfgang Finkler and Anne Schauder. Effects of Incremental Output on Incremental Natural Language Generation. In Proc. of the 10 th ECAI, pages 505–507, Vienna, Austria, August 1992.
D. Gerver. Empirical studies of simultaneous interpretation: A review and a model. In R.W. Brislin, editor, Translation: Applicatons and Research, pages 165–207. Gardner Press, New York, 1997.
Günther Görz, Marcus Kesseler, Jörg Spilker, and Hans Weber. Research on Architectures for Integrated Speech/Language Systems in Verbmobil. In Proc. of the 16 th COLING, pages 484–489, Copenhagen, Denmark, August 1996.
Andreas Hauenstein and Hans Weber. An Investigation of Tightly Coupled Speech Language Interfaces Using an Unification Grammar. In Proceedings of the Workshop on Integration of Natural Language and Speech Processing at AAAI’94, pages 42–50, Seattle, WA, 1994.
Kai Huebener, Uwe Jost, and Henrik Heine. Speech Recognition for Spontaneously Spoken German Dialogs. In ICSLP96, Philadelphia, 1996.
Susanne J. Jekat. Automatic Interpretation of Dialogue Acts. In Christa Hauenschild and Susanne Heizmann, editors, Machine Translation and Translation Theory. Perspectives of Cooperation, Text, Translation, Computational Processing (TTCP), number 1. Mouton de Gruyter, 1997.
Martin Kay. Algorithmic Schemata and Data Structures in Syntactic Processing. Technical Report CSL-80–12, Xerox Palo Alto Research Center, Palo Alto, 1980.
Martin Kay. Chart generation. In Proc. of the 34 th ACL, pages 200–204, Santa Cruz, CA, June 1996.
Hiroaki Kitano. Speech-to-Speech Translation: A Massively Parallel Memory-Based Approach. Kluwer Academic Publishers, Boston, 1994.
Marc Light. CHUMP: Partial Parsing and Underspecified Representations. In Proceedings of the ECAI-96 Workshop: Corpus-Oriented Semantic Analysis, 1996.
W.D. Marslen-Wilson. Functional Parallelism in Spoken Word Recognition. Cognition, 25: 71–102, 1987.
W.D Marslen-Wilson and A. Welsh. Processing Interactions during Word Recognition in Continuous Speech. Cognitive Psychology, 10: 29–63, 1978.
Heinrich Niemann, Elmar Nöth, Andreas Kiessling, Ralf Kompe, and Anton Batliner. Prosodic Processing and its Use in Verbmobil. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 1997.
Michael Niv. A Computational Model of Syntactic Processing: Ambiguity Resolution from Interpretation. PhD thesis, Univ. of Pennsylvania, 1993.
Manny Rayner and David Carter. Hybrid Language Processing in the Spoken Language Translator. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Munich, Germany, 1997. http://www.cam.sri.com/tr/crc064/paper.ps.Z.
Shuly Wintner and Nissim Francez. Parsing with Typed Feature Structures. In Proceedings of the 4 th International Workshop on Parking Technologies (IWPT95), pages 273–287, Prague, September 1995. Charles University.
Klaus Zechner and Alex Waibel. Using Chunk Based Partial Parsing of Spontaneous Speech in Unrestricted Domains for Reducing Word Error Rate in Speech Recognition. In COLING98P, COLING98L, 1998.
P. Zwitserlood. The Locus of Effects of Sentential-Semantic Context in Spoken-Word Processing. Cognition, 32: 25–64, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Amtrup, J.W. (1998). Incremental Speech Translation: A Layered Chart Approach. In: Dassow, J., Kruse, R. (eds) Informatik ’98. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-72283-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-72283-7_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64938-0
Online ISBN: 978-3-642-72283-7
eBook Packages: Springer Book Archive