Discriminative weighting of HMM state-likelihoods using the GPD method

IEEE Signal Processing Letters

Volumn 3, Issue 9, 1996, Pages 257-259

  Kwon, O W ^a   Un, C K ^a  

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

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; PARAMETER ESTIMATION; PROBABILITY; RECURSIVE FUNCTIONS; SPEECH RECOGNITION; WORD PROCESSING;

DISCRIMINATIVE WEIGHTING; GENERALIZED PROBABILISTIC DESCENT METHOD; HIDDEN MARKOV MODELS; STATE LIKELIHOODS; WORD RECOGNITION;

ALGORITHMS;

EID: 0030244834     PISSN: 10709908     EISSN: None     Source Type: Journal    
DOI: 10.1109/97.536594     Document Type: Article

References (5)

1. K.-Y. Su and C.-H. Lee, "Speech recognition using weighted HMM and subspace projection algorithm," IEEE Trans. Speech Audio Processing, vol. 2, no. 1, pp. 69-79, Jan. 1994.
2. F. Wolfertstetter and G. Ruske, "Discriminative state-weighting in hidden Markov models," in Proc. Int. Conf. Spoken Lang. Processing, Yokohama, Japan, Sept. 1994, pp. 219-222.
3. Y. J. Chung and C. K. Un, "Multilayer perceptions for state-dependent weightings of HMM likelihoods," Speech Commun., vol. 18, pp. 79-89, Jan. 1996.
4. W. Chou, B. H. Juang, and C. H. Lee, "Segmental GPD training of HMM based speech recognizer," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, San Francisco, CA, Mar. 1992, pp. 473-476.
5. W. Chou, C. H. Lee, and B. H. Juang, "Minimum error rate training based on N-best string models," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Minneapolis, MN, Apr. 1993, pp. 652-655.