State Level Control for Acoustic Model Training

  • German Chernykh
  • Maxim Korenevsky
  • Kirill Levin
  • Irina Ponomareva
  • Natalia Tomashenko
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8773)

Abstract

We propose a method for controlling Gaussian mixture splitting in HMM states during the training of acoustic models. The method is based on introducing special criteria of mixture quality in every state. These criteria are calculated over a separate part of the speech database. We back up states before splitting and revert to saved copies of the states whose criteria values have decreased, which makes it possible to optimize the number of Gaussians in the GMMs of the states and to prevent overfitting. The models obtained by such training demonstrate improved recognition rate with a significantly smaller number of Gaussians per state.

Keywords

acoustic modeling GMM-HMM models Gaussian splitting 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mohamed, A.-R., Dahl, G.E., Hinton, G.: Acoustic Modeling using Deep Belief Networks. IEEE Trans. Audio, Speech & Language Proc. 20(1), 14–22 (2012)CrossRefGoogle Scholar
  2. 2.
    Dahl, G.E., Dong, Y., Deng, L., Acero, A.: Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition. IEEE Trans. Audio, Speech & Language Proc. 20(1), 30–42 (2012)CrossRefGoogle Scholar
  3. 3.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. of the IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  4. 4.
    Giuliani, D., De Mori, R.: Speaker adaptation, pp. 363–404. Academic Press Inc., London (1998) R. De Mori ed.Google Scholar
  5. 5.
    Gales, M.J.F., Young, S.J.: HMM recognition in noise using parallel model combination. In: Proc. of the EuroSpeech, Berlin, Germany, September 22-25, pp. 837–840 (1993)Google Scholar
  6. 6.
    Mohri, M., Pereira, F., Riley, M.: Speech Recognition with Weighted Finite-State Transducers. In: Benesty, J., Sondhi, M.M., Huang, Y.A. (eds.) Springer Handbook of Speech Processing, pp. 559–584. Springer (2008)Google Scholar
  7. 7.
    Bilmes, J.A.: A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. Technical report TR-97-021, International Computer Science Institute, Berkley (1998)Google Scholar
  8. 8.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. J. Royal Statistical Society, Series B, 39(1), 1–38 (1977)Google Scholar
  9. 9.
    Steele, R.J., Raftery, A.E.: Performance of Bayesian Model Selection Criteria for Gaussian Mixture Models. Technical report TR-559, University of Washington, Dept. of Statistics (2009)Google Scholar
  10. 10.
    Odell, J.J.: The Use of Context in Large Vocabulary Speech Recognition (PhD Thesis), Cambridge: Cambridge University (1995)Google Scholar
  11. 11.
    Tatarnikova, M., Tampel, I., Oparin, I., Khokhlov, Y.: Building Acoustic Models for Large Vocabulary Continuous Speech Recognizer for Russian. In: Proc. of the SpeCom, St. Petersburg, Russia, June 26-29, pp. 83–87 (2006)Google Scholar
  12. 12.
    Povey, D.: Discriminative training for large vocabulary speech recognition (PhD thesis), Cambridge: Cambridge University (2003)Google Scholar
  13. 13.
    Yurkov, P., Korenevsky, M., Levin, K.: An Improvement of Robustness to Speech Loudness Change for an ASR System Based on LC-RC Features. In: Proc. of the SpeCom., Kazan, Russia, September 27-30, pp. 62–66 (2011)Google Scholar
  14. 14.
    Van den Heuvel, H., et al.: SpeechDat-E: Five Eastern European Speech Databases for Voice-Operated Teleservices Completed. In: Proc. of the InterSpeech, Aalborg, Denmark, September 3-7, pp. 2059–2062 (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • German Chernykh
    • 1
  • Maxim Korenevsky
    • 2
  • Kirill Levin
    • 2
  • Irina Ponomareva
    • 2
  • Natalia Tomashenko
    • 2
    • 3
  1. 1.Dept. of PhysicsSaint-Petersburg State UniversitySaint-PetersburgRussia
  2. 2.Speech Technology CenterSaint-PetersburgRussia
  3. 3.Dept. of Speech Information SystemsITMO UniversitySaint-PetersburgRussia

Personalised recommendations