MODELING DEPENDENCY IN ADAPTATION OF ACOUSTIC MODELS USING MULTISCALE TREE PROCESSES

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

Volumn , Issue , 1997, Pages 1863-1866

  Kannan, Ashvin ^a   Ostendorf, Mari ^a  

^a Boston University College of Engineering   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DYNAMICAL SYSTEMS; FORESTRY; SPEECH COMMUNICATION; STOCHASTIC MODELS; STOCHASTIC SYSTEMS; TREES (MATHEMATICS);

ACOUSTICS MODEL; DEPENDENCE MODEL; GAUSSIAN PROCESSES; GAUSSIANS; MODEL DEPENDENCIES; MULTISCALE PROCESS; PARAMETER DEPENDENCE; PROCESS SEGMENT; SEGMENT MODELING; STOCHASTIC DYNAMICAL SYSTEM;

SPEECH RECOGNITION;

EID: 0013208309     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. S. Ahadi and P. Woodland, "Rapid speaker adaptation using model prediction," ICASSP-95, pp. 684-687.
2. S. Chen and P. DeSouza, "Speaker adaptation by correlation (ABC)," In CSR Hub-4 DARPA Speech Workshop, February 1997.
3. K. Chou, A. Willsky and A. Benveniste, "Multiscale recursive estimation, data fusion, and regularization," IEEE Trans. on Auto. Control, 39(3):464-478, 1994.
4. S. Cox, "A speaker adaptation technique using linear regression," ICASSP-95, pp. 700-703.
5. E. Eide and H. Gish, "A parametric approach to vocal tract length normalization," ICASSP-96, pp. 346-348.
6. Q. Huo and C.-H. Lee, "On-line adaptive learning of the correlated continuous density hidden Markov models for speech recognition," ICSLP-96, pp. 985-988.
7. A. Kannan, Adaptation of Spectral Trajectory Models for Large Vocabulary Continuous Speech Recognition. PhD thesis, Boston University, 1997. Available from ftp://raven.bu.edu/pub/reports.
8. A. Kannan and M. Ostendorf, "A comparison of constrained trajectory models for large vocabulary speech recognition," Technical Report ECE-96-007, Boston University, September 1996. Available from ftp://raven.bu.edu/pub/reports.
9. A. Kannan and M. Ostendorf, "Adaptation of polynomial trajectory segment models for large vocabulary speech recognition," ICASSP-97, pp. 1411-1414.
10. A. Kannan, M. Ostendorf, D. Castanon, and W. Karl, "ML parameter estimation of a multiscale tree process using the EM algorithm," Technical Report ECE-96-009, Boston University, November 1996. Available from ftp://raven.bu.edu/pub/reports.
11. M. J. Lasry and R.M. Stern. "A Posteriori estimation of correlated jointly Gaussian mean vectors." IEEE Trans. on Pattern Analysis and Machine Intelligence, 6(4):530-535, 1984.
12. M. Luettgen, W. Karl, A. Willsky, and R. Tenney, "Multiscale representations of Markov random fields," IEEE Trans. on Signal Proc, 41(12):3377-3396, 1993.
13. B. Shahshahani, "A Markov random field approach to Bayesian speaker adaptation," IEEE Trans. on Speech and Audio Proc, 5(2):183-191, 1997.
14. G. Zavaliagkos, R. Schwartz, J. McDonough, and J. Makhoul, "Adaptation algorithms for large scale HMM recognizers," Eurospeech-95, pp. 1131-1134.