Discriminative HMMS, log-linear models, and CRFS: what is the difference?

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

Volumn , Issue , 2010, Pages 5546-5549

  Heigold, G ^a   Wiesler, S ^a   Nussbaum Thom M ^a   Lehnen, P ^a   Schluter R ^a   Ney, H ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Conditional random field; Discriminative training; Hidden Markov model; Log linear model; Speech recognition

Indexed keywords

ACOUSTIC FIELDS; ACOUSTIC MODELING; CONTINUOUS SPEECH RECOGNITION; CONVEX OPTIMIZATION;

ACOUSTICS MODEL; CONDITIONAL RANDOM FIELD; CONVEX OPTIMIZATION PROBLEMS; DISCRIMINATIVE ACOUSTIC MODEL; DISCRIMINATIVE TRAINING; GAUSSIAN-HMM; HIDDEN-MARKOV MODELS; LOGLINEAR MODEL; MODELLING TECHNIQUES; RANDOM FIELDS;

HIDDEN MARKOV MODELS;

EID: 78049400694     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495228     Document Type: Conference Paper

References (14)

1. H.-K. J. Kuo and Y. Gao, "Maximum entropy direct models for speech recognition," IEEE Transactions on Audio, Speech and Language Processing, vol. 14, no. 3, 2006.
2. Y. H. Abdel-Haleem, Conditional random fields for continuous speech recognition, Ph.D. thesis, Faculty of Engineering, University of Sheffield, Sheffield, UK, 2006.
3. J. Morris and E. Fosler-Lussier, "CRANDEM: conditional random fields for word recognition," in Interspeech, Brighton, England, Sept. 2009.
4. A. Gunawardana, M. Mahajan, A. Acero, and J.C. Platt, "Hidden conditional random fields for phone classification," in Interspeech, Lisbon, Portugal, Sept. 2005.
5. D. Yu, L. Deng, and A. Acero, "Using continuous features in the maximum entropy model," Pattern Recognition Letters, 2009.
6. M.I. Layton and M.J.F. Gales, "Augmented statistical models for speech recognition," in ICASSP, Toulouse, France, May 2006.
7. G. Heigold, G. Zweig X. Li, , and P. Nguyen, "A flat direct model for speech recognition," in ICASSP, Taipei, Taiwan, Apr. 2009.
8. T. Robinson, M. Hochberg, and S. Renals, "The use of recurrent networks in continuous speech recognition," in Automatic Speech and Speaker Recognition, K. K. Paliwal C.-H. Lee, F. K. Soong, Ed. Kluwer Academic Publishers, Norwell, MA, USA, 1996.
9. S. Wiesler, M. Nußbaum-Thom, G. Heigold, R. Schlüter, and H. Ney, "Investigations on features for log-linear acoustic models in continuous speech recognition," in ASRU, Merano, Italy, Dec. 2009.
10. G. Zweig and P. Nguyen, "Maximum mutual information multi-phone units in direct modeling," in Interspeech, Brighton, England, Sept. 2009.
11. G. Heigold, P. Lehnen, R. Schlüter, and H. Ney, "On the equivalence of Gaussian and log-linear HMMs," in Interspeech, Brisbane, Australia, Sept. 2008.
12. G. Heigold, T. Deselaers, R. Schlüter, and H. Ney, "Modified MMI/MPE: A direct evaluation of the margin in speech recognition," in ICML, Helsinki, Finland, July 2008.
13. M. Riedmiller and H. Braun, "A direct adaptive method for faster backpropagation learning: The Rprop algorithm," in ICNN, San Francisco, CA, USA, 1993.
14. G. Heigold, D. Rybach, R. Schlüter, and H. Ney, "Investigations on convex optimization using log-linear HMMs for digit string recognition," in Interspeech, Brighton, England, Sept. 2009.