Deleted strategy for MMI-based HMM training

IEEE Transactions on Speech and Audio Processing

Volumn 6, Issue 3, 1998, Pages 299-303

  Kim, Nam Soo ^a   Un, Chong Kwan ^b  

^a Seoul National University   (South Korea)

^b Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

Cross validation; Hidden markov model; Parameter training

Indexed keywords

DESIGN; MARKOV PROCESSES; MATHEMATICAL MODELS; PERFORMANCE;

MAXIMUM MUTUAL INFORMATION CRITERION;

SPEECH RECOGNITION;

EID: 0032074539     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.668824     Document Type: Article

References (12)

1. L. R. Bahl et al., "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, Tokyo, Japan, Apr. 1986, pp. 49-52.
2. B. Merialdo, "Phonetic recognition using hidden Markov models and maximum mutual information training," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, New York, NY, Apr. 1988.
3. Y. L. Chow, "Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithm," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, Albuquerque, NM, Apr. 1990, pp. 701-704.
4. Y. Normandin and S. D. Morgera, "An improved MMIE training algorithm for speaker-independent, small vocabulary, continuous speech recognition," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, Toronto, Ont., Canada, May 1991, pp. 537-540.
5. Y. Normandin, "Hidden Markov models, maximum mutual information estimation, and the speech recognition problem," Ph.D. dissertation, McGill University, Montreal, P.Q., Canada, 1991.
6. L. R. Bahl et al., "A new algorithm for the estimation of hidden Markov model parameters," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, New York, NY, Apr. 1988, pp. 493-496.
7. K. F. Lee and S. Mahajan, "Corrective and reinforcement learning for speaker-independent continuous speech recognition," Comput. Speech Lang., vol. 4, pp. 231-245, Apr. 1990.
8. W. Chou, B. H. Juang, and C. H. Lee, "Segmental GPD training of HMM based speech recognizer," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, 1992, pp. 473-476.
9. P. S. Gopalakrishnan et al., "An inequality for rational functions with applications to some statistical estimation problems," IEEE Trans. Inform. Tlieoiy, vol. 37, pp. 107-113, Jan. 1991.
10. K. F. Lee and H. W. Hon, "Speaker-independent phone recognition using hidden Markov models," IEEE Trans. Acousl., Speech, Signal Processing, vol. 37, pp. 1641-1648, Nov. 1989.
11. N. S. Kim and C. K. Un, "Frame-correlated hidden Markov model based on extended logarithmic pool," IEEE Trans. Speech Audio Processing, vol. 5, pp. 149-160, Mar. 1997.
12. P. A. Chou, "Optimal partitioning for classification and regression trees," IEEE Trans. Pattern Anal. Machine Intell, vol. 13, pp. 340-354, Apr. 1991.