A discriminative splitting criterion for phonetic decision trees

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 54-57

  Wiesler, Simon ^a   Heigold, Georg ^a   Nußbaum Thom, Markus ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Discriminative training; New paradigms; Phonetic decision trees; State tying

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; LINGUISTICS; MAXIMUM LIKELIHOOD; SPEECH COMMUNICATION; DECISION TREES; SPEECH PROCESSING;

CLASSIFICATION ERRORS; DISCRIMINATIVE TRAINING; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; MAXIMUM LIKELIHOOD PRINCIPLE; NEW PARADIGMS; PHONETIC DECISION TREE; STATE TYING; WALL STREET JOURNAL; ACOUSTICS MODEL; MINIMISATION; NEW PARADIGM; SPLITTING CRITERION; STATE OF THE ART;

DECISION TREES; ACOUSTIC MODELING;

EID: 79959818832     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. S. Young, J. Odell, and P. Woodland, "Tree-based state tying for high accuracy acoustic modelling," in Workshop on Human Language Technology, 1994.
2. W. Reichl and W. Chou, "A unified approach of incorporating general features in decision tree based acoustic modeling," in IEEE International Conference on Acoustics, Speech and Signal Processing, 1999.
3. K. Beulen and H. Ney, "Automatic question generation for decision tree based state tying," in IEEE International Conference on Acoustics, Speech, and Signal Processing, 1998.
4. P. Chou, "Optimal partitioning for classification and regression trees," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 4, pp. 340-354, 1991. (Pubitemid 21645723)
5. H. Nock, M. Gales, and S. Young, "A comparative study of methods for phonetic decision-tree state clustering," in European Conference on Speech Communication and Technology, 1997.
6. X. Liu and M. Gales, "Model complexity control and compression using discriminative growth functions," in IEEE International Conference on Acoustics, Speech and Signal Processing, 2004.
7. D. Povey and P. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002.
8. S. Gao and C. Lee, "A discriminative decision tree learning approach to acoustic modeling," in European Conference on Speech Communication and Technology, 2003.
9. J. Raviv, "Probability of error, equivocation, and the Chernoff bound," IEEE Transactions on Information Theory, vol. 16, no. 4, pp. 368-372, 1970.
10. H. Ney, "On the relationship between classification error bounds and training criteria in statistical pattern recognition," in Iberian Conference on Pattern Recognition and Image Analysis, 2003.
11. K. Fukunaga, Introduction to statistical pattern recognition. Academic Pr, 1990.
12. G. Zweig and P. Nguyen, "Maximum Mutual Information Multi-phone Units in Direct Modeling," in Interspeech, 2009.
13. G. Heigold, T. Deselaers, R. Schlüter, and H. Ney, "Modified MMI/MPE: A direct evaluation of the margin in speech recognition," in International Conference on Machine learning, 2008.
14. Z.-J. Yan, B. Zhu, Y. Hu, and R.-H. Wang, "Minimum word classification error training of HMMs for automatic speech recognition," in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2008.
15. W. Macherey, L. Haferkamp, R. Schlüter, and H. Ney, "Investigations on error minimizing training criteria for discriminative training in automatic speech recognition," in Interspeech, 2005.