Advertisement

Supervised and Unsupervised Speaker Adaptation in Large Vocabulary Continuous Speech Recognition of Czech

  • Petr Cerva
  • Jan Nouza
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3658)

Abstract

This paper deals with the problem of efficient speaker adaptation in large vocabulary continuous speech recognition (LVCSR) systems. The main goal is to adapt acoustic models of speech and to increase the recognition accuracy of these systems in tasks, where only one user is expected (e.g. voice dictation) or where the speaking person can be identified automatically (e.g. broadcast news transcription). For this purpose, we propose several modifications of the well known MLLR (Maximum Likelihood Linear Regression) method and we combine them with the MAP (Maximum A Posteriori) method. The results from a series of experiments show that the error rate of our 300K-word Czech recogniser can be reduced by about 9.9 % when only 30 seconds of supervised data are used for adaptation or by about 9.6 % when unsupervised adaptation on the same data is performed.

Keywords

Recognition Accuracy Adaptation Data Acoustic Model Word Error Rate Phonetic Transcription 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Woodland, P.C.: Speaker Adaptation: Techniques and Challenges. In: Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, Keystone (1999)Google Scholar
  2. 2.
    Gauvain, J.L., Lee, C.H.: Maximum A Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains. IEEE Trans. SAP 2, 291–298 (1994)Google Scholar
  3. 3.
    Leggetter, C.J., Woodland, P.C.: Flexible Speaker Adaptation Using Maximum Likelihood Linear Regression. In: Proc. ARPA Spoken Language Technology Workshop, pp. 104–109. Morgan Kaufmann, San Francisco (1995)Google Scholar
  4. 4.
    Nouza, J., Nejedlova, D., Zdansky, J., Kolorenc, J.: Very Large Vocabulary Speech Recognition System for Automatic Transcription of Czech Broadcast Programs. In: Proc. of Int. Conference on Spoken Language Processing (ISCLP 2004), Jeju (October 2004)Google Scholar
  5. 5.
    Huang, X.D., Acero, A., Hon, H.W.: Spoken Language Processing. Prentice-Hall, Englewood Cliffs (2001)Google Scholar
  6. 6.
    Gales, M.J.F., Woodland, P.C.: Mean and Variance Adaptation Within the MLLR Framework. Computer Speech and Language 10, 249–264 (1996)CrossRefGoogle Scholar
  7. 7.
    Nouza, J., Psutka, J., Uhlir, J.: Phonetic Alphabet for Speech Recognition of Czech. Radioengineering 6(4), 16–20 (1997)Google Scholar
  8. 8.
    Zelezny, M.: Speaker adaptation in continuous speech recognition system of Czech. PhD thesis (in Czech). Z ČU of Plzeň (2001)Google Scholar
  9. 9.
    Chesta, C., Siohan, O., Lee, C.H.: Maximum a posteriori linear regression for hidden Markov model adaptation. In: Proceedings of European Conference on Speech Communication and Technology, Budapest, Hungary, vol. 1, pp. 211–214 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Petr Cerva
    • 1
  • Jan Nouza
    • 1
  1. 1.SpeechLabTechnical University of LiberecLiberec 1Czech Republic

Personalised recommendations