Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Analysis of Different Dialog Strategies in the Slovenian Spoken Dialog System

  • Conference paper
  • First Online:
Text, Speech and Dialogue (TSD 1999)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1692))

Included in the following conference series:

  • 484 Accesses

Abstract

In the paper we first present the architecture of the Slovenian spoken dialog system. The Slovenian spoken dialog system was developed within the joint project in multilingual speech recognition and understanding Spoken Queries in European Languages (SQEL- Copernicus-1634). Such a system can handle spontaneous speech, and provide the user with correct information in the domain of air flight information retrieval. The architecture of the Slovenian system is based on the Erlangen Train Time Table Inquiry System, developed within the European Esprit project Sundial. The major modules perform word recognition, linguistic analysis, dialog management and speech synthesis.

We further describe experiments we have performed using different dialog strategies in the system - user conversations over the microphone and telephone. In the paper we describe the different dialog strategies and show some examples.

We present the modules of the Slovenian spoken information system in more detail and show some results with respect to word accuracy, semantic accuracy and dialog success rate for different dialog strategies.

This work was funded by the Commision of the European Communities and the Slovenian Ministry of Science and Technology.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. J. Peckham: Speech Understanding and Dialogue over the Telephone: an Overview of Progress in the SUNDIAL Project. In Proc. European Conf. on Speech Technology, volume 3, pages 1469–1472, 1991.

    Google Scholar 

  2. W. Eckert, T. Kuhn, H. Niemann, S. Rieck, A. Scheuer, E.G. Schukat-Talamazzini: A Spoken Dialogue System for German Intercity Train Timetable Inquiries, Proceedings of the European Conference on Speech Communication and Technology, Berlin, September 1993, pp. 1871–1874.

    Google Scholar 

  3. W. Eckert: Customizing the Erlangen Dialog Manager. Technical report, Lehrstuhl für Mustererkennung, FAU Erlangen-Nürnberg, 1996.

    Google Scholar 

  4. W. Eckert: Gesprochener Mensch-Maschine-Dialog, Ph.D.Thesis, Universität Erlangen-Nürnberg, 1996.

    Google Scholar 

  5. S. Dobrišek, J. Gros, F. Mihelič, N. Pavešić: Recording and Labelling of the GO-POLIS Slovenian Speech Database, First International Conference on Language Resources and Evaluation, edts.: A. Rubio, N. Gallardo, R. Castro, A. Tejada, May 1998, Granada, Spain, Vol. II, pp. 1089–1096.

    Google Scholar 

  6. E. G. Schukat-Talamazzini: Automatische Spracherkennung, Vieweg, Braunschweig, 1995.

    MATH  Google Scholar 

  7. I. Ipšić, F. Mihelič, N. Pavešić, E. Nöth: Slovenian Word Recognition, Proceedings of IAPR Workshop on “Speech and Image Understanding”, N. Pavešić, H. Niemann, S. Kovačić and F. Mihelič eds., Ljubljana, Slovenia, pp. 87–96, 1996.

    Google Scholar 

  8. K. Pepelnjak, F. Mihelič, N. Pavešić: Semantic Decomposition of Sentences in the System Supporting Flight Services, Journal of Computing and Information Technology, Vol. 4, No. 1, 1996, pp. 17–24.

    Google Scholar 

  9. J. Gros, N. Pavešić, F. Mihelič: Text-to-Speech Synthesis: A complete system for the Slovenian Language, Journal of Computing and Information Technology, Vol. 5, No. 1, 1997, pp. 11–19.

    Google Scholar 

  10. E. Moulines, F. Charpentier: Pitch-Synchronous Waveform Processing Techniques for Text-to-Speech Synthesis Using Diphones, Speech Communications 9, pp. 453–467, 1990.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Ipšić, I., Mihelič, F., Pavešić, N. (1999). Analysis of Different Dialog Strategies in the Slovenian Spoken Dialog System. In: Matousek, V., Mautner, P., Ocelíková, J., Sojka, P. (eds) Text, Speech and Dialogue. TSD 1999. Lecture Notes in Computer Science(), vol 1692. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48239-3_57

Download citation

  • DOI: https://doi.org/10.1007/3-540-48239-3_57

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-66494-9

  • Online ISBN: 978-3-540-48239-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics