Frame Based Postprocessor for Speech Recognition Based on Augmented Conditional Random Fields

  • Yasser Hifny Faculty of computers and information systems, University of Helwan, Egypt
Keywords: Hidden Markov models, augmented conditional random fields, deep conditional random fields, speech recognition postprocessor.

Abstract

In this paper, we present a novel postprocessor for speech recognition using the Augmented Conditional Random Field (ACRF) framework. In this framework, a primary acoustic model is used to generate state posterior scores per frame. These output scores are fed to the ACRF postprocessor for further frame based acoustic modeling.  Since ACRF explicitly integrates acoustic context modeling, the  postprocessor has the ability to discover new context information and to improve the recognition accuracy. The results on the TIMIT phone recognition task show that the proposed postprocessor can lead to significant improvements especially when Hidden Markov Models (HMMs) were used as  primary acoustic model.

References

J. Lafferty, A. McCallum, F. Pereira, Conditional random fields: Probabilistic models for segmenting and labeling sequence data, in: Proc.

ICML, 2001, pp. 282-289.

M. Layton, M. Gales, Augmented statistical models for speech recognition, in: Proc. IEEE ICASSP, Vol. 1, France, 2006, pp. 129- 132.

J. Morris, E. Fosler-Lussier, Conditional random fields for integrating local discriminative classifiers, Audio, Speech, and Language Process- ing, IEEE Transactions on 16 (3) (2008) 617-628. doi:10.1109/TASL.2008.916057.

G. Zweig, P. Nguyen, D. V. Compernolle, K. Demuynck, L. Atlas, P. Clark, G. Sell, M. Wang, F. Sha, H. Hermansky, D. Karakos, A. Jansen, S. Thomas, G. Sivaram, S. Bowman, J. Kao, Speech recognition with segmental conditional random fields: A summary of the JHU CLSP summer workshop, in: Proc. IEEE ICASSP, 2011.

M. Gales, S. Watanabe, E. Fosler-Lussier, Structured discriminative models for speech recognition, IEEE Signal Processing Magazine. [6] Y. Hifny, Conditional random fields for continuous speech recognition, Ph.D. thesis, University Of Sheffield (2006).

Y. Hifny, S. Renals, Speech recognition using augmented conditional random fields, IEEE Transactions on Audio, Speech and Language

Processing 17 (2) (2009) 354-365.

A. P. Dempster, N. M. Laird, D. B. Rubin, Maximum likelihood from incomplete data via the EM algorithm, Journal of the Royal Statistical

Society 39 (1) (1977) 1-38.

L. R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Proc. of IEEE 77 (2) (1989) 257-286.

F. Jelinek, Statistical Methods for Speech Recognition, MIT Press, 1997.

X. Huang, A. Acero, H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development, Prentice Hall,

J. Bilmes, What HMMs can do, IEICE Transactions on Information and Systems E89-D (3) (2006) 869-891.

Y. Hifny, Acoustic modeling based on deep conditional random fields, Deep Learning for Audio, Speech and Language Processing, ICML.

S. Renals, N. Morgan, H. Bourlard, M. Cohen, H. Franco, Connectionist probability estimators in HMM speech recognition, IEEE Transac- tions on Speech and Audio Processing.

N. Morgan, H. Bourlard, Continuous speech recognition: An introduction to the hybrid HMM/connectionist approach, IEEE Signal Process- ing Magazine 12 (3) (1995) 25-42.

B. Kingsbury, Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling, in: Proc. IEEE ICASSP,

, pp. 3761-3764. doi:10.1109/ICASSP.2009.4960445.

R. Prabhavalkar, E. Fosler-Lussier, Backpropagation training for multilayer conditional random field based phone recognition, in: Proc. IEEE ICASSP, Vol. 1, France, 2010, pp. 5534 - 5537.

G. Hinton, L. Deng, D. Yu, G. Dahl, A. rahman Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, , B. Kingsbury, Deep

Neural Networks for acoustic modeling in speech recognition, IEEE Signal Processing Magazine.

E. T. Jaynes, On the rationale of maximum-entropy methods, Proc. of IEEE 70 (9) (1982) 939-952.

Y. Hifny, S. Renals, N. Lawrence, A hybrid MaxEnt/HMM based ASR system, in: Proc. INTERSPEECH, Lisbon, Portugal, 2005, pp.

-3020.

A. Mohamed, D. Yu, L. Deng, Investigation of full-sequence training of Deep Belief Networks for speech recognition, in: Interspeech, 2010.

A. Halberstadt, J. Glass, Heterogeneous measurements and multiple classifiers for speech recognition, in: Proc. ICSLP, Vol. 3, Sydney, Australia, 1998, pp. 995-998.

K.-F. Lee, H.-W. Hon, Speaker-independent phone recognition using hidden Markov models, IEEE Transactions on Speech and Audio

Processing 37 (11) (1989) 1641-1648.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, P. Woodland, The HTK Book, Version 3.1, 2001.

D. Povey, Discriminative training for large vocabulary speech recognition, Ph.D. thesis, University of Cambridge (2004).

Y. Miao, PDNN: Yet Another Python Toolkit for Deep Neural Networks. URL http://www.cs.cmu.edu/ ymiao/pdnntk.html

J. Bergstra, O. Breuleux, F. Bastien, P. Lamblin, R. Pascanu, G. Desjardins, J. Turian, D. Warde-Farley, Y. Bengio, Theano: a CPU and GPU math expression compiler, in: Proceedings of the Python for Scientific Computing Conference (SciPy), 2010, oral Presentation.

Published
2015-05-02