Architectural Considerations for Conversational Systems

  • G. Görz
  • J. Spilker
  • V. Strom
  • H. Weber
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 511)


Verbmobil1 is a large German joint research project in the area spontaneous speech-to-speech translation systems which is sponsored by the German Federal Ministry for Research and Education. In its first phase (1992–1996) ca. 30 research groups in universities, research institutes and industry were involved, and it entered its second phase in January 1997. The overall goal is develop a system which supports face-to-face negotiation dialogues about the scheduling of meetings as its first domain, which will be enlarged to more general scenarios during the second project phase. For the dialogue situation it is assumed that two speakers with different mother tongues (German and Japanese) have some common knowledge of English. Whenever a speaker’s knowledge of English is not sufficient, the Verbmobil system will serve him as a speech translation device to which he can talk in his native language.


Word Recognition Recognition Rate Spontaneous Speech Beam Search Phrase Boundary 
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. Althoff, F., Drexel, G., Lungen, H., Pampel, M. and Schillo, Ch. 1996. The Treatment of Compounds in a Morphological Component for Speech Recognition. In: Gibbon, D. (Ed.): Natural Language Processing and Speech Technology. Results of the 3rd KONVENS Conference, Berlin: Mouton de Gruyter.Google Scholar
  2. Amtrup, J. 1995. ICE-INTARC Communication Environment: User’s Guide and Reference Manual. Version 1.4. Verbmobil Technical Document 14, Univ. of Hamburg.Google Scholar
  3. Amtrup, J., Benra, J. 1996. Communication in large distributed AI systems for natural language processing. Proc. of COLING-96, Kopenhagen, 35–40.Google Scholar
  4. Amtrup, J., Drexel, G., Görz, G., Pampel, M., Spilker, J. and Weber, H. 1997. The parallel time-synchronous speech-to-speech system INTARC 2.0. Proc. of ACL-97.Google Scholar
  5. Carter, D. 1994. Improving Language Models by Clustering Trainin; Sentences. Proc. of ANLP `94, Stuttgart, Germany. Extended version in Scholar
  6. Görz, G., Kesseler, M., Spilker, J. and Weber, H. 1996. Research on Architectures for Integrated Speech/Language Systems in Verbmobil. Proc. of COLING-96, Kopenhagen.Google Scholar
  7. Hauenstein, A., Weber, H. 1994. An investigation of tightly coupled time synchronous speech language interfaces. Proceedings of KONVENS-94, Vienna, Austria. Berlin: Springer.Google Scholar
  8. Kasper, W. and Krieger, H.-U. 1996. Integration of prosodic and grammatical information in the analysis of dialogs. In: Görz, G., Hölldobler, S. (Ed.): Proceedings of the 20th German Annual Conference on Artificial Intelligence, KI-96, Dresden. Berlin: Springer (LNCS).Google Scholar
  9. Kasper, W. and Krieger, H.-U. 1996. Modularizing codescriptive grammars for efficient parsing. Proc. of COLING-96, Kopenhagen, 628–633.Google Scholar
  10. Kasper, W., Krieger, H.-U., Spilker J. and Weber, H. 1996. From word hypotheses to logical form: An efficient interleaved approach. In: Gibbon, D. (Ed.): Natural Language Processing and Speech Technology. Results of the 3rd KONVENS Conference, Berlin: Mouton de Gruyter, 77–88.Google Scholar
  11. Kuhn, R. and DeMori, R 1990. A cache-based natural language model for speech recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12 (6).Google Scholar
  12. Martin, S., Liermann, J., Ney, H. 1995. Algorithms for Bigram and Trigram Word Clustering. Proc. EUROSPEECH-95, Madrid, 1253–1256.Google Scholar
  13. Petzold, A. 1995. Strategies for focal accent detection in spontaneous speech. Proc. 13t’ ICPhS Stockholm, Vol. 3, 672–675.Google Scholar
  14. Schmid, H. 1995. Improvements in Part-of-Speech Tagging with an Application to German.
  15. Strom, V. 1995. Detection of accents, phrase boundaries and sentence modality in German with prosodic features. Proc. EUROSPEECH-95, Madrid, 1995, 2039–2041.Google Scholar
  16. Strom, V. 1996. What’s in the `pure’ prosody? Proc. ICSLP 96, Philadelphia.Google Scholar
  17. Ueberla, J.P. 1994. An Extended Clustering Algorithm for Statistical Language Models, E-Print Archive Nr. 9412003,
  18. Weber, H. 1994. Time Synchronous Chart Parsing of Speech Integrating Unification Grammars with Statistics. Speech and Language Engineering, Proceedings of the Eighth Twente Workshop on Language Technology, (L. Boves, A. Nijholt, Ed.), Twente, 107119.Google Scholar
  19. Weber, H. 1995. LR-inkrementelles probabilistisches Chartparsing von Worthypothesen-mengen mit Unifikationsgrammatiken: Eine enge Kopplung von Suche und Analyse. Ph.D. Thesis, University of Hamburg, Verbmobil Report 52.Google Scholar
  20. Weber, H., Spilker, J., Görz, G. 1997. Parsing N Best Trees from a Word Lattice. In: Nebel, B. (Ed). Advances in Artificial Intelligence. Proceedings of the 2155 German Annual Conference on Artificial Intelligence, KI-97, Freiburg. Berlin: Springer (LNCS).Google Scholar

Copyright information

© Springer Science+Business Media New York 1999

Authors and Affiliations

  • G. Görz
  • J. Spilker
  • V. Strom
  • H. Weber

There are no affiliations available

Personalised recommendations