Structured discriminative models for speech recognition: An overview

IEEE Signal Processing Magazine

Volumn 29, Issue 6, 2012, Pages 70-81

  Gales, Mark John Francis ^a   Watanabe, Shinji ^b   Fosler Lussier, Eric ^c  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b MITSUBISHI ELECTRIC RESEARCH LABORATORIES   (United States)

^c OHIO STATE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTICS; CLASSIFICATION (OF INFORMATION); DEEP NEURAL NETWORKS; HIDDEN MARKOV MODELS; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES; NATURAL LANGUAGE PROCESSING SYSTEMS;

ACOUSTIC WAVEFORM; AUTOMATIC SPEECH RECOGNITION SYSTEM; DISCRIMINATIVE APPROACH; GENERATIVE CLASSIFIERS; N-GRAM LANGUAGE MODELS; NATURAL LANGUAGE PROCESSING; STRUCTURED DISCRIMINATIVE MODELS; STRUCTURED SEQUENCE;

SPEECH RECOGNITION;

EID: 85032751545     PISSN: 10535888     EISSN: None     Source Type: Journal    
DOI: 10.1109/MSP.2012.2207140     Document Type: Review

References (61)

1. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, 1989.
2. F. Jelinek, Statistical Methods for Speech Recognition. Cambridge, MA: MIT Press, 1997.
3. M. J. F. Gales and S. J. Young, "The application of hidden Markov models in speech recognition," Found. Trends Signal Processing, vol. 1, no. 3, pp. 195-304, 2008.
4. T. Joachims, "Text categorization with support vector machines: Learning with many relevant features," in Proc. ECML 1998, pp. 137-142. (Pubitemid 128067178)
5. J. Lafferty, A. McCallum, and F. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data," in Proc. ICML 2001, pp. 282-289.
6. C. Sutton, A. McCallum, and K. Rohanimanesh, "Dynamic conditional random fields: Factorized probabilistic models for labeling and segmenting sequence data," J. Mach. Learn. Res., vol. 8, pp. 693-723, 2007. (Pubitemid 46491655)
7. J. Morris and E. Fosler-Lussier, "Conditional random fields for integrating local discriminative classifiers," IEEE Trans. Audio Speech Lang. Processing, vol. 16, no. 3, pp. 617-628, 2008 .
8. N. Smith and M. J. F. Gales, "Speech recognition using SVMs," in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2002, pp. 1197-1204.
9. A. Gunawardana, M. Mahajan, A. Acero, and J. C. Platt, "Hidden conditional random fields for phone classification," in Proc. Interspeech 2005, pp. 1117-112 0. (Pubitemid 43908262)
10. Y.-H. Sung and D. Jurafsky, "Hidden conditional random fields for phone recognition," in Proc. ASRU 2009, pp. 107-112.
11. C. Saunders, J. Shawe-Taylor, and A Vinokourov, "String kernels, Fisher kernels and finite state automata," in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2002, pp. 633-640.
12. M. I. Layton and M. J. F. Gales, "Acoustic modeling using continuous rational kernels," J. VLSI Signal Processing Syst. Signal Image Video Technol., vol. 48, no. 1, pp. 67-82, 2007.
13. S. Wiesler, M. Nußbaum-Thom, G. Heigold, R. Schlüter, and H. Ney, "Investigations on features for log-linear acoustic models in continuous speech recognition," in Proc. ASRU 2009, pp. 52-57.
14. S.- X. Zhang, A. Ragni, and M. J. F. Gales, "Structured log-linear models for noise robust speech recognition," IEEE Signal Processing Lett., vol. 17, no. 11, pp. 945-948, 2010.
15. A. Ragni and M. J. F. Gales, "Derivative kernels for noise robust ASR," in Proc. of ASRU 2011, pp. 119-124.
16. S .-X. Zhang and M. J. F. Gales, "Extending noise robust structured support vector machines to larger vocabulary tasks," in Proc. ASRU 2011, pp. 18-23.
17. G. Zweig and P. Nguyen, "A segmental CRF approach to large vocabulary continuous speech recognition," in Proc. ASRU 2009, pp. 152-157.
18. M. I. Layton, "Augmented statistical models for classifying sequence data," Ph.D. dissertation, Eng. Dept., Cambridge Univ., 2006.
19. H. K. J. Kuo and Y. Gao, "Maximum entropy direct models for speech recognition," IEEE Trans. Audio Speech Lang. Processing, vol. 14, no. 3, pp. 873-881, 2006. (Pubitemid 46547649)
20. Y. Hifny and S. Renals, "Speech recognition using augmented conditional random fields," IEEE Trans. Audio Speech Lang. Processing, vol. 17, no. 2, pp. 354-365, 2009.
21. B. Roark, M. Saraclar, M. Collins, and M. Johnson, "Discriminative language modeling with conditional random fields and the perceptron algorithm," in Proc. ACL 2004, pp. 47-54.
22. J. A. Bilmes, "Graphical models and automatic speech recognition," in Mathematical Foundations of Speech and Language Processing, R. Rosenfeld, M. Ostendorf, S. Khudanpur, and M. Johnson, Eds. New York: Springer-Verlag, 2003, pp. 191-245.
23. A. J. Viterbi, "Error bounds for convolutional codes and asymptotically optimum decoding algorithm," IEEE Trans. Inform. Theory, vol. 13, no. 2, pp. 260-269, 1982.
24. A. Nadas, "A decision theoretic formulation of a training problem in speech recognition and a comparison of training by unconditional versus conditional maximum likelihood," IEEE Trans. Acoustics Speech Signal Processing, vol. 31, no. 4, pp. 814-817, 198 3. (Pubitemid 14455162)
25. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP 2002, vol. 1, pp. 13-17.
26. F. Sha and L. K. Saul, "Large margin hidden Markov models for automatic speech recognition," in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2007, pp. 1249-1256.
27. C. M. Bishop, Pattern Recognition and Machine Learning. New York: Springer-Verlag, 2006.
28. A. L. Berger, S. A. Della Pietra, and V. J. Della-Pietra, "A maximum entropy approach to natural language processing," Comput. Linguist., vol. 22, no. 1, pp. 39-72, 1996.
29. V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer-Verlag, 2000.
30. I. Tsochantaridis, T. Hofmann, T. Joachims, and Y. Altun, "Support vector machine learning for interdependent and structured output spaces," in Proc. ICML 2004, pp. 104-112.
31. P. Nguyen, G. Heigold, and G. Zweig, "Speech recognition with flat direct models," IEEE J. Select. Topics Signal Processing, vol. 4, no. 6, pp. 994-1006, 2010.
32. M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," Comput. Speech Lang., vol. 16, no. 1, pp. 69-88, 2002.
33. Y.-H. Sung, C. Boulis, C. Manning, and D. Jurafsky, "Regularization, adaptation, and non-independent features improve hidden conditional random fields for phone classification," in Proc. ASRU 2007, pp. 347-352.
34. G. Heigold, R. Schlüter, and H. Ney, "On the equivalence of Gaussian HMM and Gaussian HMM-like hidden conditional random fields," in Proc. Interspeech 2007, pp. 1721-1724.
35. G. Zweig, P. Nguyen, D. van Compernolle, K. Demuynck, L. Atlas, P. Clark, G. Sell, M. Wang, F. Sha, H. Hermansky, D. Karakos, A. Jansen, S. Thomas, G. S. V. S. Sivaram, S. Bowman, and J. Kao, "Speech recognition with segmental conditional random fields: A summary of the JHU CLSP Summer workshop," in Proc. ICASSP 2011, pp. 5044-5047.
36. M. Ostendorf, V. Digilakis, and O. Kimball, "From HMMs to segment models: A unified view of stochastic modeling for speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, no. 5, pp. 360-378, 1 996. (Pubitemid 126753024)
37. C. N. J. Yu and T. Joachims, "Learning structural SVMs with latent variables," in Proc. 26th Annu. Int. Conf. Machine Learning, 2009, pp. 1169-1176.
38. S. Sarawagi and W. W. Cohen, "Semi-Markov conditional random fields for information extraction," in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2004, pp. 1185-1192.
39. I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun, "Large margin methods for structured and interdependent output variables," J. Mach. Learn. Res., vol. 6, pp. 1453-1484, Sept. 2005.
40. W. Byrne, "Minimum Bayes risk estimation and decoding in large vocabulary continuous speech recognition," IEICE Special Issue Stat. Modeling Speech Recognition, vol. 89, no. 3, pp. 900-90 7, 2006.
41. M. J. F. Gales, "Discriminative models for speech recognition," in Proc. Information Theory and Applications Workshop, 2007, pp. 170-176.
42. M. Collins, "Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms," in Proc. EMNLP 2002, vol. 10, pp. 1-8.
43. S. F. Chen and R. Rosenfeld, "Efficient sampling and feature selection in whole sentence maximum enropy language models," in Proc. ICASSP 1999, p p. 549-552.
44. S. Wiesler, A. Richards, Y. Kubo, R. Schlüter, and H. Ney, "Feature selection for log-linear acoustic models," in Proc. ICASSP 2011, pp. 5324-5327.
45. C. Chelba and A. Acero, "Adaptation of maximum entropy capitalizer: Little data can help a lot," Comput. Speech Lang., vol. 20, no. 4, pp. 382-399, 2006. (Pubitemid 44142003)
46. Y.-H. Sung, C. Boulis, and D. Jurafsky, "Maximum conditional likelihood linear regression and maximum a posteriori for hidden conditional random fields speaker adaptation," in Proc. ICASSP 2008, pp. 4293-4296.
47. J. Loof, R. Schlüter, and H. Ney, "Discriminative adaptation for log-linear acoustic models," in Proc. Interspeech 2010, pp. 1648-1651.
48. M. J. F. Gales and F. Flego, "Discriminative classifiers with adaptive kernels for noise robust speech recognition," Comput. Speech Lang., vol. 24, no. 4, pp. 648-662, 2010.
49. C. Cortes, P. Haffner, and M. Mohri, "Rational kernels: Theory and algorithms," J. Mach. Learn. Res., vol. 5, pp. 1035-1062, Dec. 2004.
50. C. Longworth, "Kernel methods for text-independent speaker verification," Ph.D. dissertation, Cambridge Univ., 201 0.
51. T. Jaakkola and D. Hausser, "Exploiting generative models in discriminative classifiers," in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 1999, pp. 487-493.
52. R. C. van Dalen, A. Ragni, and M. J. F. Gales, "Efficient decoding with continuous rational kernels using the expectation semiring," Cambridge Univ. Eng. Dept, Tech. Rep. CUED/F-INFENG/TR674, 2 012.
53. S. F. Chen, "Shrinking exponential language models," in Proc. HLT-NAACL, 2009, pp. 468-476.
54. M. Collins, B. Roark, and M. Saraclar, "Discriminative syntactic language modeling for speech recognition," in Proc. of ACL 2005, pp. 507-514.
55. E. Arisoy, M. Sara̧lar, B. Roark, and I. Shafran, "Syntactic and sub-lexical features for Turkish discriminative language models," in Proc. ICASSP 2010, pp. 5538-5541.
56. S. Watanabe, T. Hori, and A. Nakamura, "Large vocabulary continuous speech recognition using WFST-based linear classifier for structured data," in Proc. Interspeech 2010, pp. 346-349.
57. M. Lehr and I. Shafran, "Learning a discriminative weighted finite-state transducer for speech recognition," IEEE Trans. Audio Speech Lang. Processing, vol. 19, no. 5, pp. 1360-1367, 2011.
58. T. Oba, T. Hori, A. Nakamura, and A. Ito, "Round-robin duel discriminative language models," IEEE Trans. Audio Speech Lang. Processing, vol. 20, no. 4, pp. 1244-1255, 201 2.
59. K. Demuynck, D. Seppi, P. van Compernolle, D. Nguyen, and G. Zweig, "Integrating meta-information into examplar-based speech recognition with segmental conditional random fields," in Proc. ICASSP 2011, pp. 5048-5051.
60. T. Joachims, T. Finley, and C.-N. Yu, "Cutting-plane training of structural SVMs," Mach. Learn., vol. 77, no. 1, pp. 27-59, 2 009.
61. A. Yuille, A. Rangarajan, and A. L. Yuille, "The concave-convex procedure (CCCP)," in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2003, pp. 915-936.