A unified view for discriminative objective functions based on negative exponential of difference measure between strings

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

Volumn , Issue , 2009, Pages 1633-1636

  Nakamura, Atsushi ^a   McDermott, Erik ^a   Watanabe, Shinji ^a   Katagiri, Shigeru ^b  

^a NTT Communication Science Laboratories   (Japan)

^b DOSHISHA UNIVERSITY   (Japan)

Author keywords

Automatic speech recognition; Discriminative training; Generalized objective function; Laplace Stieltjes transform; Negative exponential function

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; DISCRIMINATIVE TRAINING; GENERALIZED OBJECTIVE FUNCTION; LAPLACE-STIELTJES TRANSFORM; NEGATIVE EXPONENTIAL FUNCTION;

ACOUSTICS; BLIND SOURCE SEPARATION; LAPLACE TRANSFORMS; SIGNAL PROCESSING; STEREOPHONIC BROADCASTING;

SPEECH RECOGNITION;

EID: 70349205533     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2009.4959913     Document Type: Conference Paper

References (10)

1. X. He, et al., "Discriminative learning in sequential pattern recognition," IEEE SP Mag. 25, 5, pp. 14-36, September 2008.
2. D. Povey, Discriminative training for large vocabulary Speech Recognition, Ph.D. thesis, Cambridge University, 2004.
3. E. McDermott, et al., "Discriminative training for large vocabulary speech recognition using Minimum Classification Error," IEEE Trans. ASLP, 15, 1, pp. 203-223, January 2007.
4. D. Povey and P. Woodland, "Minimum Phone Error and I-smoothing for improved discriminative training," in Proc. IEEE ICASSP, pp. 105-108, 2002.
5. J. Zheng and A. Stolcke, "Improved discriminative training using phone lattices," in Proc. Interspeech, pp. 2125-2128, 2005.
6. W. Macherey, et al., "Investigations on error minimizing training criteria for discriminative training in automatic speech recognition," in Proc. Eurospeech, pp. 2133-2136, 2005.
7. D. Povey, et al., "Boosted MMI for model and feature-space discriminative training," in Proc.IEEE ICASSP, pp. 4057-4060, 2008.
8. E. McDermott and A. Nakamura, "Flexible discriminative training based on equal error group scores obtained from an error-indexed forward-backward algorithm," in Proc. Interspeech, pp. 2398-2401, 2008.
9. G. Heigold, et al., "Modified MMI/MPE: A direct evaluation of the margin in speech recognition," In Proc.ICML, pp. 384-391, 2008.
10. G. Saon and D. Povey, "Penalty function maximization for large margin HMM training," In Proc. Interspeech, pp. 920-923, 2008.