On the equivalence of Gaussian HMM and Gaussian HMM-like Hidden Conditional Random Fields

International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007

Volumn 2, Issue , 2007, Pages 1273-1276

  Heigold, Georg ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Maximum entropy methods; Parameter estimation; Speech recognition

Indexed keywords

ACOUSTIC MODELING; GAUSSIAN DISTRIBUTION; IMAGE SEGMENTATION; MAXIMUM ENTROPY METHODS; MAXIMUM PRINCIPLE;

ACOUSTICS MODEL; FRAME-BASED; GAUSSIAN-HMM; HIDDEN CONDITIONAL RANDOM FIELDS; HYBRID APPROACH; LOCAL OPTIMA; MAXIMUM-ENTROPY METHODS; OPTIMIZATION PROBLEMS; PARAMETERS ESTIMATION; ROBUST FORMULATIONS;

SPEECH RECOGNITION;

EID: 56149106440     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. W. Macherey and H. Ney, "A comparative study on maximum entropy and discriminative training for acoustic modeling in automatic speech recognition," in Proc. European Conference on Speech Communication and Technology, Geneva, Switzerland, Sept. 2003, pp. 493 - 496.
2. C. Sutton and A. McCallum, "An introduction to conditional random fields for relational learning," in Introduction to Statistical Relational Learning. MIT Press, 2006.
3. A. Gunawardana, M. Mahajan, A. Acero, and J. C. Platt, "Hidden conditional random fields for phone classification," in Proc. of the Int. Conf. on Spoken Language Processing (ICSLP), Lisbon, Portugal, Sept. 2005.
4. D. Povey and P.C. Woodland, "Frame discrimination training for HMMs for large vocabulary speech recognition," in Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Phoenix, AZ, Mar. 1999, pp. 333 - 336.
5. H.-K. J. Kuo and Y. Gao, "Maximum entropy direct models for speech recognition," IEEE Trans. on Audio, Speech and Language Processing, vol. 14, no. 3, pp. 873 - 881, 2006.
6. J. Lafferty, A. McCallum, and F. Pereira, "Conditional random fields: probabilistic models for segmenting and labeling sequence data," in Proc. 18th Int. Cong. Machine Learning, San Francisco, CA, 2001, pp. 282 - 289.
7. D. Kershaw, T. Robinson, and M. Hochberg, "Context-dependent classes in a hybrid recurrent network-HMM speech recognition system," in Advances Neural Information Processing Systems 8 (NIPS'8), 1996, pp. 750 - 756.
8. 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, 2007.
9. E. S. Ristad and P. N. Yianilos, "Towards EM-style algorithms for a posteriori optimization of normal mixtures," in Proc. IEEE Symposium on Information Theory, August 1998.
10. W. Macherey, R. Schlüter, and H. Ney, "Discriminative training with tied covariance matrices," in Proc. Int. Conf. on Spoken Language Processing (ICSLP), Jeju Island, Korea, Oct. 2004, pp. 681 - 684.
11. J. Lööf, M. Bisani, Ch. Gollan, G. Heigold, B. Hoffmeister, Ch. Plahl, R. Schlüter, and H. Ney, "The 2006 RWTH parliamentary speeches transcription system," in Proc. of the Int. Conf. on Spoken Language Processing (ICSLP), Pittsburgh, PA, Sept. 2006, pp. 105 - 108.