Structured SVMs for automatic speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 21, Issue 3, 2013, Pages 544-555

  Zhang, Shi Xiong ^a   Gales, Mark J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

large margin; log linear models; Structured support vector machines

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; CONTEXT DEPENDENT; DISCRIMINATIVE MODELS; FEATURE SPACE; GAUSSIANS; GENERATIVE MODEL; LARGE MARGIN; LARGE VOCABULARY SPEECH RECOGNITION; LOGLINEAR MODEL; PARALLELIZATION STRATEGIES; SEQUENCE CLASSIFICATION; STRUCTURED SUPPORTS; TRAINING ALGORITHMS; TRAINING PROCESS;

HIDDEN MARKOV MODELS; SPEECH RECOGNITION;

SUPPORT VECTOR MACHINES;

EID: 84872193462     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2227734     Document Type: Article

References (46)

1. S.-X. Zhang and M. J. F. Gales, "Extending noise robust structured support vector machines to larger vocabulary tasks," in Proc. ASRU, Waikoloa, Hawaii, 2011.
2. M. J. F. Gales, D. Kim, P. Woodland, H. Chan, D. Mrva, R. Sinha, and S. Tranter, "Progress in the CU-HTK broadcast news transcription system," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1513-1525, Sep. 2006. (Pubitemid 46547578)
3. B. Taskar, V. Chatalbashev, D. Koller, and C. Guestrin, "Learning structured prediction models: A large margin approach," in Proc. Int. Conf. Mach. Learn., 2005, pp. 896-903.
4. G. H. Bakir, T. Hofmann, B. Schölkopf,A. J. Smola, B. Taskar, and S. V. N. Vishwanathan, Predicting Structured Data (Neural Information Processing). Cambridge, MA: MIT Press, 2007.
5. M. Gales and S. Young, "The application of hidden Markov models in speech recognition," Foundat. Trends Signal Process., p. 2007.
6. P. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models in speech recognition," Comput. Speech Lang., vol. 16, no. 1, pp. 25-48, Jan. 2002.
7. B.-H. Juang and S. Katagiri, "Discriminative learning for minimum error classification," IEEE Trans. Signal Process., vol. 40, no. 12, p. 3043, 1992.
8. W. Byrne, "Minimum Bayes risk estimation and decoding in large vocabulary continuous speech recognition," IEICE Trans., vol. 89-D, no. 3, pp. 900-907, 2006.
9. F. Sha and L. K. Saul, "Large margin hidden Markov models for automatic speech recognition," Neural Inf. Process. Syst., pp. 1249-1256, 2007.
10. J. Keshet, C.-C. Cheng, M. Stoehr, and D. A. McAllester, "Direct error rate minimization of hidden Markov models," in Proc. Interspeech, 2011, pp. 449-452.
11. G. Heigold, G. Zweig, X. Li, and P. Nguyen, "A flat direct model for speech recognition," in Proc. ICASSP, 2009, pp. 3861-3864.
12. G. Zweig and P. Nguyen, "A segmental CRF approach to large vocabulary continuous speech recognition," in Proc. ASRU, 2009.
13. M. Layton and M. Gales, "Augmented statistical models for speech recognition," in Proc. ICASSP, Toulouse, France, 2006, pp. 129-132.
14. S.-X. Zhang, A. Ragni, and M. J. F. Gales, "Structured log linear models for noise robust speech recognition," IEEE Signal Process. Lett., vol. 17, no. 11, pp. 945-948, Nov. 2010.
15. G. Heigold, "A log-linear discriminative modeling framework for speech recognition," Ph.D. dissertation, RWTH Aachen Univ., Aachen, Germany, 2010.
16. 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.
17. B. Taskar, "Learning structured prediction models: A large margin approach," Ph.D. dissertation, Stanford Univ., Stanford, CA, 2005.
18. B. Taskar, C. Guestrin, and D. Koller, "Max-margin Markov networks," in Proc. NIPS, 2004.
19. D. Povey, "Discriminative Training for Large Vocabulary Speech Recognition," Ph.D. dissertation, Cambridge Univ., 2004.
20. T. Joachims, T. Finley, and C.-N. J. Yu, "Cutting-plane training of structural SVMs," Mach. Learn., vol. 77, no. 1, pp. 27-59, 2009.
21. O. Birkenes, T. Matsui, and K. Tanabe, "Isolated-word recognition with penalized logistic regression machines," in Proc. ICASSP, 2006, vol. 1, pp. 405-408.
22. J. Lafferty, A. McCallum, and F. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data," in Proc. Int. Conf. Mach. Learn., 2001.
23. G. Zweig and P. Nguyen, "From flat direct models to segmental CRF models," in Proc. ICASSP, 2010, pp. 5530-5533.
24. K. Crammer and Y. Singer, "On the algorithmic implementation of multiclass kernel-based vector machines," J. Mach. Learn. Res., vol. 2, pp. 265-292, 2002.
25. V. Venkataramani, S. Chakrabartty, and W. Byrne, "Support vector machines for segmental minimum Bayes risk decoding of continuous speech," in Proc. ASRU, 2003.
26. S.-X. Zhang and M. J. F. Gales, "Structured support vector machines for noise robust continuous speech recognition," in Proc. Interspeech, Florence, Italy, 2011, pp. 989-992.
27. T. S. Jaakkola and D. Haussler, "Exploiting generative models in discriminative classifiers," in Proc. 1998 Conf. Adv. Neural Inf. Process. Syst. II, Cambridge, MA, 1999, pp. 487-493, MIT Press.
28. A. Ragni and M. J. F. Gales, "Derivative kernels for noise robustASR," in Proc. ASRU, Waikoloa, Hawaii, 2011.
29. A. Ragni and M. J. F. Gales, "Structured discriminative models for noise robust continuous speech recognition," in Proc. ICASSP, Prague, Czech Repubic, 2011, pp. 4788-4791.
30. Z. Ghahramani and M. I. Jordan, "Factorial Hidden Markov models," Mach. Learn., vol. 29, pp. 245-273, 1997. (Pubitemid 127510040)
31. S. Sarawagi and W. W. Cohen, "Semi-Markov conditional random fields for information extraction," in Proc. NIPS, 2005.
32. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, "Object detection with discriminatively trained part-based models," IEEE Trans, Pattern Anal.Mach. Intell., vol. 32, no. 9, pp. 1627-1645, Sep. 2010.
33. C.-N. Yu and T. Joachims, "Learning structural SVMs with latent variables," in Proc. ICML, 2009.
34. A. Yuille, A. Rangarajan, and A. L. Yuille, "The concave-convex procedure (CCCP)," in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2002.
35. Y. Singer and N. Srebro, "Pegasos: Primal estimated sub-gradient solver for SVM," in Proc. ICML, 2007, pp. 807-814.
36. A. Globerson, T. Y. Koo, X. Carreras, and M. Collins, "Exponentiated gradient algorithms for log-linear structured prediction," in Proc. ICML, 2007, pp. 305-312.
37. 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, 2005.
38. T. Jebara, "Discriminative, generative and imitative learning," Ph.D. dissertation, Media Lab, Mass. Inst. of Technol., Cambridge, MA, 2001.
39. J. Li, M. Yuan, and C.-H. Lee, "Approximate test risk bound minimization through soft margin estimation," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 8, pp. 2393-2404, Nov. 2007.
40. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "BoostedMMI for model and feature-space discriminative training," in Proc. ICASSP, 2008, pp. 4057-4060.
41. M. Layton, "Augmented statistical models for classifying sequence data," Ph.D. dissertation, Cambridge Univ., Cambridge, U.K., 2006.
42. M. J. F. Gales, D. Pye, and P. Woodland, "Variance compensation within theMLLR framework for robust speech recognition and speaker adaptation," in Proc. ICSLP, 1996, vol. 3, pp. 1832-1835.
43. A. Acero, L. Deng, T. Kristjansson, and J. Zhang, "HMM Adaptation using vector Taylor series for noisy speech recognition," in Proc. ICSLP, Beijing, China, 2000.
44. H. Liao and M. Gales, "Joint uncertainty decoding for robust large vocabulary speech recognition," Cambridge Univ., Cambridge, U.K., Tech. Rep. CUED/F-INFENG/TR552, Nov. 2006.
45. O. Kalinli, M. L. Seltzer, and A. Acero, "Noise adaptive training using a vector Taylor series approach for noise robust automatic speech recognition," in Proc. ICASSP, 2009, pp. 3825-3828.
46. F. Flego and M. Gales, "Factor analysis based VTS and JUD noise estimation and compensation," Cambridge Univ., Cambridge, U.K., Tech. Rep. CUED/F-INFENG/TR653, 2011 [Online]. Available: http://mi. eng.cam.ac.uk/~mjfg