Solving large-margin hidden Markov model estimation via semidefinite programming

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 8, 2007, Pages 2383-2392

  Li, Xinwei ^a,b   Jiang, Hui ^a  

^a YORK UNIVERSITY   (Canada)

^b NUANCE COMMUNICATIONS   (United States)

Author keywords

Continuous density hidden Markov models (CDHMMs); Convex optimization; Large margin classifers; Large margin hidden Markov models; Semidefinite programming (SDP)

Indexed keywords

BOUNDEDNESS; CONNECTED DIGITS; CONTINUOUS-DENSITY HIDDEN MARKOV MODELS (CDHMMS); GRADIENT DESCENTS; LARGE-MARGIN CLASSIFERS; LARGE-MARGIN HIDDEN MARKOV MODELS; MARKOV MODELS; OPTIMIZATION ALGORITHMS; OPTIMIZATION METHODS; RELAXATION CONDITIONS; SEMIDEFINITE PROGRAMING; SEMIDEFINITE PROGRAMMING (SDP); TRAINING METHODS; WORD ERROR RATES;

COMPUTATIONAL GRAMMARS; CONVEX OPTIMIZATION; DEMODULATION; ESTIMATION; OBJECT RECOGNITION; OPTIMIZATION; SPEECH ANALYSIS; SPEECH RECOGNITION; WAVELET TRANSFORMS;

HIDDEN MARKOV MODELS;

EID: 44849126208     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2007.905151     Document Type: Article

References (27)

1. F. Alizadeh, "Interior point methods in semidefinite programming with applications to combinatorial optimization," Soc. Industrial Appl. Math. (SIAM) J. Optim., vol. 5, pp. 13-51, 1995.
2. Y. Altun, I. Tsochantaridis, and T. Hofmann, "Hidden Markov support vector machines," in Proc. 20th Int. Conf. Mach. Learn. (ICML-2003), Washington, D.C, 2003, pp. 1-8.
3. S. J. Benson, Y.Ye, and X. Zhang, "Solving large-scale sparse semidefinite programs for combinatorial optimization," Soc. Industrial Appl. Math. (SIAM) J. Optim., vol. 10, no. 2, pp. 443-461, 2000.
4. P. Biswas and Y. Ye, "Semidefinite programming for ad hoc wireless sensor network localization," in Proc. Inf. Process. Sensor Netw. (IPSN), Berkeley, CA, Apr. 2004, pp. 46-54.
5. S. Boyd, L. E. Ghaoui, E. Feron, and V. Balakrishnan, "Linear matrix inequalities in system and control theory," Stud. Appl. Math. (SIAM), vol. 15, Jun. 1994.
6. S. Boyd and L. Vandenberghe, Convex Optimization. Cambridge, U.K.: Cambridge Univ. Press, 2004.
7. M. Fukuda and M. Kojima, "Interior-Point Methods for Lagrangian Duals of Semidefinite Programs," Dept. Math. Comput. Sci., Tokyo Inst. Technol., Tokyo, Japan, 2000, Tech. Rep. B-365.
8. M. X. Goemans and D. P.Williamson, "Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming," J. ACM, vol. 42, pp. 1115-1145, 1995.
9. D. Goldfarb and K. Scheinberg, "Interior point trajectories in semidefinite programming," Soc. Industrial Appl. Math. (SIAM) J. Optim., vol. 8, pp. 871-886, 1998.
10. H. Jiang, K. Hirose, and Q. Huo, "Robust speech recognition based on bayesian prediction approach," IEEE Trans. Speech Audio Process., vol. 7, no. 4, pp. 426-440, Jul. 1999.
11. H. Jiang, Discriminative Training for Large Margin HMMs Dept. Comput. Sci. Eng., York Univ., Toronto, ON, Canada, 2004, Tech. Rep. CS-2004-01.
12. H. Jiang, F. Soong, and C.-H Lee, "A dynamic in-search data selection method with its applications to acoustic modeling and utterance verification," IEEE Trans. Speech Audio Process., vol. 13, no. 5, pp. 945-955, Sep. 2005.
13. H. Jiang, X. Li, and C. Liu, "Large margin hidden Markov models for speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1584-1595, Sep. 2006.
14. R. G. Leonard, "A database for speaker-independent digit recognition," in Proc. ICASSP'84, 1984, pp. 328-331.
15. X. Li, H. Jiang, and C. Liu, "Large margin HMMs for speech recognition," in Proc. 2005 IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP'05), Philadelphia, PA, Mar. 2005, pp. V-513-V-516.
16. X. Li and H. Jiang, "A constrained joint optimization method for large margin HMM estimation," in Proc. IEEE Workshop Autom. Speech Recognition Understanding, 2005, pp. 151-156.
17. Y. Nesterov and A. Nemirovskii, "Interior-point polynomial algorithms in convex programming," in SIAM Studies in Applied Mathematics. Philadelphia, PA: SIAM, 1994, vol. 13.
18. X. Li, "Large margin hidden markov models for speech recognition," M.S thesis, Dept. Comput. Sci. Eng.,York Univ., Toronto, ON, Canada, 2005.
19. X. Li and H. Jiang, "Solving large margin HMM estimation via semi-definite programming," in Proc. Int. Conf. Spoken Lang. Process. (ICSLP'06), Pittsburgh, PA, Apr. 2006, pp. 2414-2417.
20. C. Liu, H. Jiang, and X. Li, "Discriminative training of CDHMMs for maximum relative separation margin," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP'05), Philadelphia, PA,Mar. 2005, pp. V-101-V-104.
21. C. Liu, H. Jiang, and L. Rigazio, "Maximum relative margin estimation of HMMs based on N-best string models for continuous speech recognition," in Proc. 2005 IEEE Workshop Autom. Speech Recognition Understanding, 2005, pp. 420-425.
22. F. Sha and L. Saul, "Large margin hidden Markov models for automatic speech recognition," Adv. Neural Inf. Process. Syst. (NIPS) 19, pp. 1249-1256, 2006.
23. A. M. So and Y. Ye, "Theory of semidefinite programming for sensor network localization," Dept. Manag. Sci. Eng., Stanford Univ., Stanford, CA, 2004, Tech. Rep..
24. B. Taskar, C. Guestrin, and D.Koller, "Max-margin Markov networks," in Proc. Neural Inf. Process. Syst. Conf. (NIPS'03), Vancouver, BC, Canada, Dec. 2003.
25. I. Tsochantaridis, T. Hofmann, T. Joachims, and Y. Altun, "Support vector machine learning for interdependent and structured output spaces," in Proc. 21th Int. Conf. Mach. Learn. (ICML), 2004, pp. 104-112.
26. L. Vandenberghe and S. Boyd, "Semidefinite programming," SIAM Rev. 38, pp. 49-95, Mar. 1996.
27. V. N. Vapnik, Statistical Learning Theory. New York: Wiley, 1998.