A trust region based optimization for maximum mutual information estimation of HMMS in speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2009, Pages 3757-3760

  Yan, Zhi Jie ^a,c   Liu, Cong ^a   Hu, Yu ^a   Jiang, Hui ^b  

^a UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA   (China)

^b YORK UNIVERSITY   (Canada)

^c MICROSOFT RESEARCH   (United States)

Author keywords

Hidden Markov models; Optimization methods; Speech recognition

Indexed keywords

DISCRIMINATIVE TRAINING; EFFICIENT GLOBAL OPTIMIZATION; GAUSSIAN MIXTURES; MAXIMUM MUTUAL INFORMATION ESTIMATIONS; OPTIMIZATION CONVERGENCE; OPTIMIZATION METHOD; OPTIMIZATION METHODS; QUADRATIC OBJECTIVE FUNCTIONS; RECOGNITION ERROR; RELATIVE ERRORS; SPEECH RECOGNITION PERFORMANCE; TRUST REGION; TRUST-REGION METHODS;

ACOUSTICS; COMPUTATIONAL GRAMMARS; CONSTRAINED OPTIMIZATION; GLOBAL OPTIMIZATION; HIDDEN MARKOV MODELS; OBJECT RECOGNITION; OPTIMIZATION; SIGNAL PROCESSING; STEREOPHONIC BROADCASTING;

SPEECH RECOGNITION;

EID: 70349218147     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2009.4960444     Document Type: Conference Paper

References (7)

1. J. Nocedal and S. J. Wright, Numerical Optimization, Springer, 2nd edition, 2006.
2. P. Liu, C. Liu, H. Jiang, F. Soong, and R.-H. Wang, "A Constrained Line Search Optimization Method for Discriminative Training of HMMs," IEEE Trans. on Audio, Speech and Language Processing, vol. 16, no. 1, pp. 900-909, 2008.
3. Hui Jiang and Xinwei Li, A General Approximation-Optimization Approach to Large Margin Estimation of HMMs, chapter 7, pp. 103-120, Robust Speech Recognition and Understanding. I-TECH Education and Publishing, 2007.
4. K. Vertanen, "HTK Wall Street Journal (WSJ) training recipe," http://www.inference.phy.cam.ac.uk/kv227/htk/.
5. P. Woodland, J. Odell, V. Valtchev, and S. Young, "Large vocabulary continuous speech recognition using HTK," in Proc. ICASSP1994, 1994, vol. 2, pp. 125-128.
6. S. Young, et al., The HTK Book, Cambridge University, 2006, Revised for HTK version 3.4.
7. Z.-J. Yan, B. Zhu, Y. Hu, and R.-H. Wang, "Minimum Word Classification Error Training of HMMs for Automatic Speech Recognition," in Proc. ICASSP2008, 2008, pp. 4521-4524.