Error-weighted discriminative training for HMM parameter estimation

8th International Conference on Spoken Language Processing, ICSLP 2004

Volumn , Issue , 2004, Pages 1661-1664

  Willett, Daniel ^a  

^a Speech Dialog Systems   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ERRORS; MAXIMUM LIKELIHOOD; MAXIMUM LIKELIHOOD ESTIMATION; SPEECH RECOGNITION; STEREOPHONIC BROADCASTING;

DISCRIMINATIVE TRAINING; EXPERIMENTAL EVALUATION; MAXIMUM MUTUAL INFORMATION; PARAMETER ESTIMATE; PARAMETER TRAINING; SENTENCE ERRORS; WEIGHTING FACTORS; WORD ERROR RATE REDUCTIONS;

PARAMETER ESTIMATION;

EID: 64149112593     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. R. Schlüter, W. Macherey, B. Müller, H. Ney, Comparison of discriminative training criteria and optimization methods for speech recognition, Speech Communication 34, pp. 287-310, 2001.
2. P. C. Woodland, D. Povey, Large Scale Discriminative Training for Speech Recognition, ISCA ITRW ASR 2000 Workshop: Challenges for the Millennium, pp. 7-16, Paris, 2000.
3. P. S. Gopalakrishnan, D. Kanevsky, D. Nadas, D. Nahamoo, M. Picheny, Decoder Selection based on Cross-Entropies, IEEE ICASSP 1988.
4. V. Goel, S. Axelrod, R. Gopinath, P. Olsen, K. Visweswariah, Discriminative Estimation of Subspace Precision and Mean (SPAM) Models, ISCA Eurospeech 2003, pp. 2617-2620.
5. M. M. Hochberg, L. T. Niles, J. T. Foote, H. F. Silverman, Hidden Markov Model / Neural Network Training Techniques for Connected Alpha-Digit Speech Recognition, ICASSP 1991.
6. V. Valtchev, Discriminative Methods in HMM-based Speech Recognition, Ph.D. thesis, Cambridge University Engineering Department, UK.
7. P. S. Gopalakrishnan, D. Kanevsky, D. Nadas, D. Nahamoo, An Inequality for Rational Functions with Applications to Some Statistical Estimation Problems, IEEE Transactions on Information Theory, Vol. 37, No. 1, 1991, pp. 107-113.
8. Y. Normandin, An Improved MMIE Training Algorithm for Speaker-Independent, Small Vocabulary, Continuous Speech Recognition, IEEE ICASSP 1991, pp. 537-540.
9. B. Merialdo, Phonetic Recognition using Hidden Markov Models and Maximum Mutual Information Training, IEEE ICASSP 1988.
10. M. Riedmiller, H. Braun, A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP algorithm, IEEE International Conference on Neural Networks 1993.