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.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
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)
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)
Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. of the IEEE 77(2), 257–286 (1989)
Giuliani, D., De Mori, R.: Speaker adaptation, pp. 363–404. Academic Press Inc., London (1998) R. De Mori ed.
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)
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)
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)
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)
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)
Odell, J.J.: The Use of Context in Large Vocabulary Speech Recognition (PhD Thesis), Cambridge: Cambridge University (1995)
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)
Povey, D.: Discriminative training for large vocabulary speech recognition (PhD thesis), Cambridge: Cambridge University (2003)
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)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Chernykh, G., Korenevsky, M., Levin, K., Ponomareva, I., Tomashenko, N. (2014). State Level Control for Acoustic Model Training. In: Ronzhin, A., Potapova, R., Delic, V. (eds) Speech and Computer. SPECOM 2014. Lecture Notes in Computer Science(), vol 8773. Springer, Cham. https://doi.org/10.1007/978-3-319-11581-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-11581-8_54
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11580-1
Online ISBN: 978-3-319-11581-8
eBook Packages: Computer ScienceComputer Science (R0)