Stochastic Modelling of Sentence Semantics in Speech Recognition

  • Włodzimierz Kasprzak
  • Paweł Przybysz
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 95)


A stochastic approach to spoken sentence recognition is proposed for the purpose of an automatic voice-based dialogue system. Three main tasks are distinguished: word recognition, word chain filtering and sentence recognition. The first task is solved by typical acoustic processing followed by phonetic word recognition with the use of Hidden Markov Models (HMM) and Viterbi search. For the second solution an N-gram model of natural language is applied and a token-passing search is designed for the filtering of important word chains. The third task is solved due to a semantic HMM of sentences. The final sentence is recognized and a meaning is assigned to its elements with respect to given application domain. A particular spoken sentence recognition system has been implemented for train connection queries.


Hide Markow Model Word Recognition Speech Recognition Language Model Speech Recognition System 
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. 1.
    Benesty, J., Sondhi, M.M., Huang, Y. (eds.): Springer Handbook of Speech Processing. Springer, Berlin (2008)Google Scholar
  2. 2.
    Bennacef, S., Devillers, L., Rosset, S., Lamel, L.: Proceedings of International Conference on Spoken Language Processing, ICSLP 1996, pp. 550–553 (1996)Google Scholar
  3. 3.
    Chen, S.F., Goodman, J.: Computer Speech and Language 13, 359–393 (1999)Google Scholar
  4. 4.
    Chen, S.F., Rosenfeld, R.: IEEE Trans. on Speech and Audio Processing 8(1), 37–50 (2000)Google Scholar
  5. 5.
    Fellbaum, C. (ed.): WordNet. An Electronic Lexical Database. The MIT Press, Cambridge (1998)zbMATHGoogle Scholar
  6. 6.
    Hayes, P.J., Andersen, P.M., Safier, S.: Proceedings of 23rd Annual Meeting of ACL, Chicago, Illinois, pp. 153–160 (1985)Google Scholar
  7. 7.
    Jelinek, F., Lafferty, J.D., Mercer, R.L.: Basic methods of probabilistic context-free grammars. In: Laface, P., De Mori, R. (eds.) Speech Recognition and Understanding: Recent Advances, Trends, and Applications, pp. 345–360. Springer, Berlin (1992)Google Scholar
  8. 8.
    Kasprzak, W.: Rozpoznawanie obrazów i sygnałów mowy. Warsaw University of Technology Press, Warszawa (2009)Google Scholar
  9. 9.
    Katz, S.M.: IEEE Trans. Acoustics, Speech and Signal Proc. ASSP 35, 400–401 (1987)Google Scholar
  10. 10.
    Rabiner, L., Juang, B.H.: Fundamentals of Speech Recognition. Prentice Hall, New York (1993)Google Scholar
  11. 11.
    Russell, S., Norvig, P.: Artificial Intelligence. A Modern Approach. Prentice Hall, New York (2002)Google Scholar
  12. 12.
    Young, S.: HMMs and related speech recognition technologies. In: Benesty, J., Sondhi, M.M., Huang, Y. (eds.) Springer Handbook of Speech Processing, pp. 539–555. Springer, Berlin (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Włodzimierz Kasprzak
    • 1
  • Paweł Przybysz
    • 1
  1. 1.Institute of Control and Computation EngineeringWarsaw University of TechnologyWarszawaPoland

Personalised recommendations