UNIFIED FRAMEWORK FOR ACOUSTIC TOPOLOGY MODELLING: ML-SSS AND QUESTION-BASED DECISION TREES

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 1355-1358

  Singer, Harald ^a   Nakamura, Atsushi ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

DECISION TREES; LINGUISTICS; SPEECH COMMUNICATION; SPEECH RECOGNITION;

CONTEXT DEPENDENT; LARGE VOCABULARY; MA XIMUM LIKELIHOODS; MAXIMUM-LIKELIHOOD; MODEL MAXIMUM; PHONETIC DECISION TREE; SHARED CONTEXT; SPLITTINGS; TOPOLOGY MODELING; UNIFIED FRAMEWORK;

MAXIMUM LIKELIHOOD;

EID: 85009181766     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. L. Bahl, P. deSouza, P. Gopalakrishnan, D. Nahamoo, and M. Picheny. Decision trees for phonological rules in continuous speech. In Proc. ICASSP, pages 185-188, 1991.
2. H. Nock, M. Gales, and S. Young. A comparative study of methods for phonetic decision-tree state clustering. In Proc. EuroSpeech, pages 111-114, 1997.
3. S. Young, J. Odell, and P. Woodland. Tree-based state tyingfor high accuracy acoustic modelling. In Proc. DARPA Workshop, pages 286-291, 1994.
4. M. Ostendorf and H. Singer. HMM topology design using maximum likelihood successive state splitting. Computer Speech and Language, 11(1):17-41, 1997.
5. P. Chou. Optimal partitioning for classification and regression trees. IEEE Trans. PAMI, 13(4):340-354, April 1991.
6. K. Beulen and H. Ney. Automatic question generation for decision tree based state tying. In Proc. ICASSP, volume II, pages 805-808, May 1998.
7. D. Willett, C. Neukirchen, J. Rottland, and G. Rigoll. Refining tree-based state clustering by means of formal concept analysis, balanced decision trees and automatically generated model-sets. In Proc. ICASSP, pages 565-568, 1999.
8. R. Singh, B. Raj, and R. Stern. Automatic clustering and generation of contextual questions for tied states in hidden markov model. In Proc. ICASSP, pages 117-120, 1999.
9. S. Sagayama and S. Honma. Estimation of unknown context using a phoneme environment clustering algorithm. In Proc. ICSLP, pages 361-364, Kobe, 1990.
10. M. Hwang, X. Huang, and F. Alleva. Predicting unseen triphones with Senones. IEEE Trans. Speech Audio, 4(6):412-419, November 1996.
11. A. Nakamura, S. Matsunaga, T. Shimizu, M. Tonomura, and Y. Sagisaka. Japanese speech database for robust speech recognition. In Proc. ICSLP, pages 137-140, Philadelphia, 1996.
12. M. Tonomura, T. Kosaka, and S. Matsunaga. Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation. Computer Speech and Language, 10:117-132, 1996.
13. H. Yamamoto and Y. Sagisaka. Multi-class composite n-gram based on connection direction. In Proc. ICASSP, pages 533- 536, 1999.
14. T. Hori, M. Katoh, A. Ito, and M. Kohda. A study on HM-Nets using phonetic decision tree-based successive state splitting. IEICE TRANSACTIONS, J80-D-II(10):2645-2654, October 1997. (in Japanese).