A Comparative Study of Methods for Phonetic Decision-Tree State Clustering

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 111-114

  Nock, H J ^a   Gales, M J F ^a   Young, S J ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

DECISION TREES; SPEECH COMMUNICATION;

APPROXIMATE METHODS; COMPARATIVES STUDIES; CONTEXT DEPENDENT MODELING; HMM-BASED SYSTEMS; KEY ISSUES; PARTITIONING METHODS; PHONETIC DECISION TREE; STATE CLUSTERING; TREE SIZE;

LINGUISTICS;

EID: 85135161923     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. LR Bahl, PV de Souza, PS Gopalakrishnan, D Nahamoo, and MA Picheny. Robust methods for using context-dependent features and models in a continuous speech recognizer. In ProclCASSP, pages 533-536,1994.
2. G Boulianne and P Kenny. Optimal tying of HMM mixture densities using decision trees. In Proc ICSLP, pages 350-354, 1996.
3. L Breiman, J Friedman, RA Olshen, and CJ Stone. Classification and Regression Trees. Wadsworth Inc, 1994.
4. P Chou. Optimal partitioning for classification and regression trees. IEEE Trans PAMl, 13(4):340-354,1991.
5. A Lazarides, Y Normandin, and R Kuhn. Improving decision trees for acoustic modelling. In Proc ICSLP, pages 1053-1057, 1996.
6. H Nock. Contextual clustering for triphone-based speech recognition. Master's thesis, Cambridge University Engineering Department, 1996.
7. H Singer and M Ostendorf. Maximum likelihood sucessive state splitting. In Proc ICASSP, pages 601-605, 1996.
8. SJ Young, JJ Odell, and PC Woodland. Tree-based state tying for high accuracy acoustic modelling. In ARPA Human Language Technology Workshop, pages 286-291,1994.