Effective acoustic model clustering via decision-tree with supervised learning

Speech Communication

Volumn 46, Issue 1, 2005, Pages 1-13

  Park, Junho ^a   Ko, Hanseok ^a  

^a Korea University   (South Korea)

Author keywords

Acoustic modeling; Decision tree; Large vocabulary continuous speech recognition

Indexed keywords

ACOUSTICS; ALGORITHMS; DECISION THEORY; MATHEMATICAL MODELS; PARAMETER ESTIMATION; SPEECH RECOGNITION; STATISTICAL METHODS; TREES (MATHEMATICS);

ACOUSTIC MODELING; DECISION-TREE; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; SUPERVISED LEARNING;

LEARNING SYSTEMS;

EID: 17444397713     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2004.12.003     Document Type: Article

References (20)

1. Aubert, X., et al., 1996. A bottom-up approach for handling unseen triphones in large vocabulary continuous speech recognition. In: Proc. ICSLP'96, pp. 14-17
2. Bahl, L.R., et al., 1994. Robust methods for using context-dependent features and models in a continuous speech recognizer. In: Proc. ICASSP'94, I/533-I/536, vol. 1
3. Boulianne, G., Kenny, P., 1996. Optimal tying of HMM mixture densities using decision-trees. In: Proc. ICSLP'96, pp. 350-353
4. V.V. Digalakis Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers IEEE Trans. Speech Audio Process 4 4 1996 281 289
5. R.W. Hamming Coding and information theory 1986 Prentice-Hall
6. Hwang, M., Huang, X., 1992. Subphonetic modeling for speech recognition. In: Proc. DARPA Speech and Natural Language Workshop, pp. 174-179
7. M. Hwang Shared-distribution hidden Markov models for speech recognition IEEE Trans. Speech Audio Process. 1 4 1993 414 420
8. O. Kwon, and J. Park Korean large vocabulary continuous speech recognition with morpheme-based recognition units Speech Communicat. 39 2003 287 300
9. K. Lee Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition IEEE Trans. Acoustics Speech Signal Process. 38 4 1990 599 609
10. J. Ming, and F. Smith A Bayesian triphone model Comput. Speech Language 13 1999 195 206
11. T.M. Mitchell Machine learning 1997 The McGraw-Hill
12. Nock, H.J., et al., 1997. A comparative study of methods for phonetic decision-tree clustering. In: Proc. EUROSPEECH'97
13. Odell, J.J., 1995. The use of context in large vocabulary speech recognition. Ph.D. Thesis, University of Cambridge
14. J.R. Quinlan Decision-trees and decision making IEEE Trans. System Man Cybernet. 20 2 1990 339 346
15. Reichl, W., Chou, W., 1998. Decision-tree state tying based on segmental clustering for acoustic modeling. In: Proc. IEEE Int. Conf. on Acoustic, Speech, and Signal Processing, pp. 801-804
16. W. Reichl, and W. Chou Robust decision-tree state tying for continuous speech recognition IEEE Trans. Speech Audio Process. 8 5 2000 555 566
17. Woodland, P.C., Young, S.J., 1992. Benchmark DARPA RM results with the HTK portable HMM toolkit. In: Proc. DARPA Continuous Speech Recognition Workshop, pp. 71-76
18. Woodland, P.C., et al., 1994. The development of the 1994 HTK large vocabulary speech recognition system. In: Proc. ARPA SLT Workshop
19. Young, S.J., 1992. The general use of tying in phoneme-based HMM speech recognizers. In: Proc. ICASSP'92
20. Young, S.J., et al., 1994. Tree-based state tying for high accuracy acoustic modeling. In: Proc. ARPA Workshop on Human Language Technology