Knowledge-based adaptive decision tree state tying for conversational speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 7, 2007, Pages 2160-2168

  Hu, Rusheng ^a,b   Zhao, Yunxin ^a  

^a University of Missouri   (United States)

^b Capital One   (United States)

Author keywords

Acoustic modeling; Approximate Bayesian; Decision tree state tying; Implicit prior; Speech recognition

Indexed keywords

ACOUSTIC MODELING; ACOUSTIC MODELS; APPROXIMATE BAYESIAN; BAYESIAN LEARNING FRAMEWORKS; CONVERSATIONAL SPEECH RECOGNITION; DECISION RULES; DECISION TREE STATE TYING; DOMAIN SPECIFICS; GREEDY SEARCHES; IMPLICIT PRIOR; LARGE DATUM; MODEL QUALITIES; PHONETIC DECISION TREES; PRIOR KNOWLEDGE; PRONUNCIATION VARIATIONS; RECOGNITION ACCURACIES; SPEAKER ADAPTATIONS; TRANSFORMATION OF TREES; TREE GROWING; TREE STRUCTURES;

ACOUSTICS; BAYESIAN NETWORKS; DECISION TREES; KNOWLEDGE BASED SYSTEMS; SPEECH ANALYSIS; TELEMEDICINE;

SPEECH RECOGNITION;

EID: 64549109650     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2007.901830     Document Type: Article

References (25)

1. S. Seneff, "The use of subword linguistic modeling for multiple tasks in speech recognition," Speech Commun., vol. 42, pp. 373-390, Apr. 2004.
2. S. Greenberg, "Speaking in shorthand-A syllable-centric perspective for understanding pronunciation variation," Speech Commun., vol. 29, no. 2-4, pp. 159-176, Nov. 1999.
3. D. Jurafsky, W.Ward, J. Zhang, K. Herold, X. Yu, and S. Zhang, "What kind of pronunciation variation is hard for triphones to model?," in Proc. 2001 IEEE Int. Conf. Acoust., Speech, Signal Process., Salt Lake City, UT, May 2001, pp. 577-580.
4. T. Hain, "Implicit modeling of pronunciation variation in automatic speech recognition," Speech Commun., vol. 26, pp. 171-188, 2005.
5. M. Riley, B. Byrne, M. Finke, S. Khudanpur, A. Ljolje, J. McDonough, H. Nock, M. Saraclar, C. Wooters, and G. Zavaliagkos, "Stochastic pronunciation modeling from hand-labeled phonetic corpra," Speech Commun., vol. 29, pp. 209-224, Nov. 1999.
6. M. Saraclar, H. J. Nock, and S. Khudanpur, "Pronunciation modeling by sharing Gaussian densities across phonetic models," Comput. Speech Lang., vol. 14, pp. 137-160, 2000.
7. W. Reichl and W. Chou, "Robust decision tree state tying for continuous speech recognition," IEEE Trans. Speech Audio Process., vol. 8, no. 5, pp. 555-566, Sep. 2000.
8. J.-T. Chien and S. Furui, "Predictive hidden Markov model selection for speech recognition," IEEE Trans. Speech Audio Process., vol. 13, no. 3, pp. 377-387, May 2005.
9. I. Shafran and M. Ostendorf, "Acoustic model clustering based on syllable structure," Comput. Speech Lang., vol. 17, no. 4, pp. 311-328, 2003.
10. S. Wang and Y. Zhao, " Online Bayesian tree-structured transformation of HMMs with optimal model selection for speaker adaptation," IEEE Trans. Speech Audio Process., vol. 9, no. 6, pp. 663-677, Sep. 2001.
11. K. Shinoda and C.-H. Lee, "A structural Bayes approach to speaker adaptation," IEEE Trans. Speech Audio Process., vol. 9, no. 3, pp. 276-287, Mar. 2001.
12. S. J. Young, J. J. Odell, and P. C. Woodland, "Tree-based state tying for high accuracy acoustic modeling," in Proc. ARPA Human Lang. Technol. Workshop, Mar. 1994, pp. 307-312.
13. H. Strik and C. Cucchiarini, "Modeling pronunciation variation for ASR: A survey of the literature," Speech Commun., vol. 29, pp. 225-246, 1999.
14. Y. Zhao, X. Zhang, R-S. Hu, J. Xue, X. Li, L. Che, R. Hu, and L. Schopp, "An automatic captioning system for telemedicine," in Proc. ICASSP, Toulouse, France, 2006, pp. I-957-I-960.
15. W. L. Buntine, "A Theory of Learning Classification Rules," Ph.D. dissertation, School of Comput. Sci., Univ. Technology, Sydney, 1992.
16. H. A. Chipman, E. I. George, and R. E. McCulloch, "Bayesian CART model search," J. Amer. Statist. Assoc., vol. 93, no. 443, pp. 935-948, Sep. 1998.
17. D. Denison, C. Holmes, B. Malick, and A. Smith, Bayesian Methods for Nonlinear Classification and Regression. New York:Wiley, 2002.
18. G. Schwarz, "Estimating the dimension of a model," Ann. Statist., vol. 6, no. 2, pp. 465-471, 1978.
19. P. Hilton and J. Pedersen, "Catalan numbers, their generalization, and their uses," Math. Intell., vol. 13, no. 2, pp. 64-75, 1991.
20. B. Launay, O. Siohan, A. Surendran, and C.-H. Lee, "Towards knowledge- based features forHMMbased large vocabulary automatic speech recognition," in Proc. ICASSP02, 2002, vol. 1, pp. I-817-I-820.
21. quot;The HTK Toolkit." [Online]. Available: http://htk.eng.cam.ac. uk/
22. R. R. Kneser and H. Ney, "Improved backing-off for M-gram language modeling," in Proc. ICASSP, 1995, pp. 181-184.
23. A. Stolcke, "SRILM-An extensible language modeling toolkit," in Proc. ICSLP, Denver, CO, Sep. 2002, pp. 901-904.
24. X. Zhang, Y. Zhao, and L. Schopp, "A novel method of language modeling for automatic captioning in tc video teleconferencing," IEEE Trans. Inf. Technol. Biomed., vol. 11, no. 3, pp. 332-337, May 2007.
25. X. Li and Y. Zhao, "A fast and memory-efficient N-gram language model lookup method for large vocabulary continuous speech recognition," Comput. Speech Lang., vol. 21, pp. 1-25, 2007.