Towards a Dynamic Adjustment of the Language Weight

  • Georg Stemmer
  • Viktor Zeissler
  • Elmar Nöth
  • Heinrich Niemann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2166)


Most speech recognition systems use a language weight to reduce the mismatch between the language model and the acoustic models. Usually a constant value of the language weight is chosen for the whole test set. In this paper, we evaluate the possibility to adapt the language weight dynamically to the state of the dialogue or to the current utterance. Our experiments show, that the gain in performance, that can be achieved with a dynamic adjustment of the language weight on our data is very limited. This result is independent of the information source that is used for the adaption of the language weight.


Language Model Acoustic Model Dynamic Adjustment Speech Recognition System Spontaneous Speech 
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.
    V. Zeissler: Verbesserte Linguistische Gewichtung in einem Spracherkenner. Master thesis (in German), Chair for Pattern Recognition, University of Erlangen-Nuremberg, Erlangen (2001)Google Scholar
  2. 2.
    H. Bourlard and H. Hermansky and N. Morgan: Towards Increasing Speech Recognition Error Rates. Speech Communication, vol. 18 (1996), 205–231CrossRefGoogle Scholar
  3. 3.
    Ramesh R. Sarukkai and Dana H. Ballard: Word Set Probability Boosting for Improved Spontaneous Dialogue Recognition: The AB/TAB Algorithm. University of Rochester, Rochester (1995)Google Scholar
  4. 4.
    X. Huang and M. Belin and F. Alleva and M. Hwang: Unified Stochastic Engine (USE) for Speech Recognition. Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Minneapolis (1993) 636–639Google Scholar
  5. 5.
    F. Gallwitz: Integrated Stochastic Models for Spontaneous Speech Recognition. Dissertation, University of Erlangen-Nuremberg, Erlangen (to appear)Google Scholar
  6. 6.
    W. Eckert and F. Gallwitz and H. Niemann: Combining Stochastic and Linguistic Language Models for Recognition of Spontaneous Speech. Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Atlanta (1996) 423–426Google Scholar
  7. 7.
    W. Wahlster, Verbmobil: Foundations of Speech-to-Speech Translation. Springer, New York, Berlin (2000)zbMATHGoogle Scholar
  8. 8.
    G. Stemmer and E. Nöth and H. Niemann: The Utility of Semantic-Pragmatic Information and Dialogue-State for Speech Recognition in Spoken Dialogue Systems. Proc. of the Third Workshop on Text, Speech, Dialogue, Brno (2000) 439–444Google Scholar
  9. 9.
    V. Fischer and S.J. Kunzmann: Acoustic Language Model Classes for a Large Vocabulary Continuous Speech Recognizer. Proc. Int. Conf. on Spoken Language Processing, Bejing (2000) 810–813Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Georg Stemmer
    • 1
  • Viktor Zeissler
    • 1
  • Elmar Nöth
    • 1
  • Heinrich Niemann
    • 1
  1. 1.Chair for Pattern RecognitionUniversity of Erlangen-NurembergErlangenGermany

Personalised recommendations