Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 224-227

  McDermott, Erik ^a   Watanabe, Shinji ^a   Nakamura, Atsushi ^a  

^a NTT Communication Science Laboratories   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CENTRAL OBSERVATIONS; CLASSIFICATION ERRORS; CORPUS OF SPONTANEOUS JAPANESE; DISCRIMINATIVE TRAINING; FINITE DIFFERENCE; FUNCTIONALS; FUNDAMENTAL THEOREMS; MAXIMUM MUTUAL INFORMATION; MINIMUM PHONE ERROR; OBJECTIVE FUNCTIONS;

FEATURE EXTRACTION; STEREOPHONIC BROADCASTING;

SPEECH COMMUNICATION;

EID: 70450194926     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. W. Macherey, L. Haferkamp, R. Schlueter, and H. Ney, "Investigations on Error Minimizing Training Criteria for Discriminative Training in Automatic Speech Recognition," in Proc. Eurospeech, 2005.
2. E. McDermott, T.J. Hazen, J. Le Roux, A. Nakamura, and S. Katagiri, "Discriminative training for large vocabulary speech recognition using Minimum Classification Error," IEEE Transactions on Audio, Speech and Language Processing, vol. 15, no. 1, pp. 203-223, January 2007.
3. D. Povey and P.C. Woodland, "Minimum Phone Error and Ismoothing for improved discriminative training," in Proc. IEEE ICASSP, 2002, vol. 1, pp. 105-108.
4. Q. Fu, D.-S. Mansjur, and B.-H. Juang, "Non-Uniform Error Criteria for Automatic Pattern and Speech Recognition," in Proc. IEEE ICASSP, 2008, pp. 1853-1856.
5. X. Li, H. Jiang, and C. Liu, "Large margin HMMs for speech recognition," in Proc. IEEE ICASSP, 2005, vol. 5, pp. 513-516.
6. J. Li, Z.-J. Yan, C.-H. Lee, and R.-H. Wang, "A study on soft margin estimation for LVCSR," in Proc. ASRU, 2007.
7. D. Yu, L. Deng, X. He, and A. Acero, "Large-margin Minimum Classification Error training: A theoretical risk perspective," in Computer Speech and Language, 2008, vol. 22, pp. 415-429.
8. F. Sha and L. K. Saul, "Large margin hidden Markov models for automatic speech recognition," in Proc. of NIPS, 2007, pp. 1249-1456.
9. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for Model and Feature-Space Discriminative Training," in Proc. IEEE ICASSP, 2008, pp. 4057-4060.
10. G. Saon and D. Povey, "Penalty Function Maximization for Large Margin HMM Training," in Proc. Interspeech, 2008, pp. 920-923.
11. G. Heigold, T. Deselaers, R. Schlueter, and H. Ney, "Modified MMI/MPE: a Direct Evaluation of the Margin in Speech Recognition," in Proc. International Conference on Machine Learning (ICML), Helsinki, Finland, 2008.
12. A. Nakamura, E. McDermott, S. Watanabe, and S. Katagiri, "A Unified View for Discriminative Objective Functions Based on Negative Exponential of Difference Measure Between Strings," in Proc. IEEE ICASSP, 2009.
13. E. McDermott and A. Nakamura, "String and Lattice based Discriminative Training for the Corpus of Spontaneous Japanese Lecture Transcription Task," in Proc. Interspeech, 2007, pp. 2082-2085.
14. H.-A. Chang and J. R. Glass, "Discriminative Training of Hierarchical Acoustic Models for Large Vocabulary Continuous Speech Recognition," in Proc. IEEE ICASSP, 2009, pp. 4481-4484.