Hidden Markov Models for Understanding in a Dialogue System

  • Fernando Blat
  • Sergio Grau
  • Emilio Sanchis
  • María José Castro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)

Abstract

In this work, we present an approach to Automatic Speech Understanding based on stochastic models. In a first phase, the input sentence is transduced into a sequence of semantic units by using hidden Markov models. In a second phase, a semantic frame is obtained from this sequence of semantic units. We have studied some smoothing techniques in order to take into account the unseen events in the training corpus. We have also explored the possibility of using specific hidden Markov models, depending on the dialogue state. These techniques have been applied to the understanding module of a dialogue system of railway information in Spanish. Some experimental results with written and speech input are presented.

References

  1. 1.
    Pallet, D.S., et al.: The 1994 benchmark test for the ARPA spoken language program. In: Proceedings of ARPA Workshop on Spoken Language Technology (1995)Google Scholar
  2. 2.
    Bonafonte, A., et al.: Desarrollo de un sistema de diálogo oral en dominios restringidos. In: Primeras Jornadas de Tecnología del Habla, Sevilla, Spain (2000)Google Scholar
  3. 3.
    Zue, V., et al.: Jupiter: A telephone-based conversational interface for weather information. IEEE Trans. on Speech and Audio Processing 8(1) (2000)Google Scholar
  4. 4.
    Seneff, S.: TINA: A natural language system for spoken language applications. Computational Linguistics 18(1), 61–86 (1992)Google Scholar
  5. 5.
    Ward, W.: Evaluation of the CMU ATIS system. In: Proc. of DARPA Speech and Natural Language Workshop, pp. 101–105 (1991)Google Scholar
  6. 6.
    Lamel, L., et al.: The LIMSI Arise system. Speech Communication 31(4), 339–354 (2000)CrossRefGoogle Scholar
  7. 7.
    Levin, E., Pieraccini, R.: Concept-Based Spontaneous Speech Understanding System. In: Proc. 4th Eurospeech 1995, pp. 555–558 (1995)Google Scholar
  8. 8.
    Bonneau-Maynard, H., Lefèvre, F.: Investigating stochastic speech understanding. In: Proc. of IEEE ASRU (2001)Google Scholar
  9. 9.
    Macherey, K., Och, F.J., Ney, H.: Natural Language Understanding Using Statistical Machine Translation. In: Proc. 7th Eurospeech 2001, pp. 2205–2208 (2001)Google Scholar
  10. 10.
    Fillmore, C.J.: The case for case. Universals in Linguistic Theory, 1–90 (1968)Google Scholar
  11. 11.
    Sanchis, E., García, F., Galiano, I., Segarra, E.: Applying dialogue constraints to the understanding process in a Dialogue System. In: Proc. of 5th TSD, pp. 389–395 (2002)Google Scholar
  12. 12.
    Vilar, D., Castro, M.J., Sanchis, E.: Connectionist classification and specific stochastic models in the understanding process of a dialogue system. In: Proc. Eurospeech 2003, pp. 645–648 (2003)Google Scholar
  13. 13.
    Forney Jr., G.D.: The Viterbi algorithm. Proc. IEEE, 268–278 (1973)Google Scholar
  14. 14.
    Segarra, E., Hurtado, L.: Construction of Language Models using Morfic Generator Grammatical Inference MGGI Methodology. In: Proc. Eurospeech 1997, pp. 2695–2698 (1997)Google Scholar
  15. 15.
    Segarra, E., et al.: Extracting Semantic Information Through Automatic Learning Techniques. IJPRAI 16(3), 301–307 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Fernando Blat
    • 1
  • Sergio Grau
    • 1
  • Emilio Sanchis
    • 1
  • María José Castro
    • 1
  1. 1.Departament de Sistemes Informàtics i ComputacióUniversitat Politècnica de ValènciaValènciaSpain

Personalised recommendations