Parameter estimation of a target-directed dynamic system model with switching states

Signal Processing

Volumn 81, Issue 5, 2001, Pages 975-987

  Togneri, Roberto ^a   Ma, Jeff ^b   Deng, Li ^b  

^a Univ W   (Australia)

^b UNIVERSITY OF WATERLOO   (Canada)

Author keywords

Extended Kalman filter; Maximum likelihood; Target directed dynamical system

Indexed keywords

COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; ITERATIVE METHODS; MATHEMATICAL MODELS; NONLINEAR CONTROL SYSTEMS; PARAMETER ESTIMATION; PROBLEM SOLVING; STATE SPACE METHODS;

EXPECTATION-MAXIMIZATION ALGORITHMS; STATE-SPACE NONLINEAR SYSTEM MODELS; TARGET-DIRECTED DYNAMICAL SYSTEMS;

KALMAN FILTERING;

EID: 0035337891     PISSN: 01651684     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0165-1684(00)00276-0     Document Type: Article

References (24)

1. Dempster A.P., Laird N.M., Rubin D.B. Maximum likelihood from incomplete data via the EM algorithm. J. R. Statist. Soc. Ser. B. 39:1977;1-38.
2. Deng L. A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition. Speech Commun. 24:1998;299-323.
3. L. Deng, J. Ma, A statistical coarticulatory model for the hidden vocal-tract-resonance dynamics, Proceedings of Eurospeech 1999, September 1999, pp. 1499-1502.
4. Deng L., Shen X. Maximum likelihood in statistical estimation of dynamic systems: decomposition algorithm and simulation results. Signal Process. 57:1997;65-79.
5. Deng L., Sun D.X. A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features. JASA. 95(5):1994;2702-2719.
6. Digalakis V., Rohlicek J.R., Ostendorf M. ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition. IEEE Trans. Speech Audio Process. 1(4):1993;431-442.
7. S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice-Hall, Englewood cliffs, NJ, 1999, pp. 156-252 (Chapter 4).
8. Kashyap R.L. Maximum likelihood identification of stochastic linear systems. IEEE Trans. Automat. Control. AC-15:1970;25-34.
9. Ljung L. Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systems. IEEE Trans. Automat. Control. AC-24:1979;36-50.
10. R.K. Mehra, Approaches to adaptive filtering, IEEE Trans. Automat. Control AC-17 (1972) 693-698.
11. J. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice-Hall, Englewood cliffs, NJ, 1995, pp. 384-394 (Lesson 24).
12. J. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice-Hall, Englewood Cliffs, NJ, 1995, pp. 259-276 (Lesson 18).
13. J. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice-Hall, Englewood Cliffs, NJ, 1995, pp. 317-344 (Lesson 21).
14. X.L. Meng, D.B. Rubin, Maximum likelihood estimation via the ECM algorithm: a general framework, Biometrika 80 (2) (1993) 267-288.
15. Nelson L.W., Stear E. The simultaneous on-line estimation of parameters and states in linear systems. IEEE Trans. Automat. Control. AC-12:1967;438-442.
16. Nettleton D. Convergence properties of the EM algorithm in constrained parameter spaces. Canad. J. Statist. 27(3):1999;639-648.
17. Ostendorf M., Digalakis V.V., Kimball O.A. From HMM's to segment models: a unified view of stochastic modeling for speech recognition. IEEE Trans. Speech Audio Process. 4(5):1996;360-378.
18. J. Picone et al., Initial evaluation of hidden dynamic models on conversational speech, Proceedings of ICASSP 1999, March 1999, pp. 109-112.
19. Puskorius G.V., Feldkamp L.A. Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks. IEEE Trans. Neural Networks. 5(2):1994;279-297.
20. Rabiner L.R. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE. (77):1989;257-286.
21. H.B. Richards, J.S. Bridle, The HDM: a segmental hidden dynamic model of coarticulation, Proceedings of ICASSP 1999, March 1999, pp. 357-360.
22. Shumway R.H., Stoffer D.S. Dynamic linear models with switching. J. Amer. Statist. Assoc. 86(415):1991;763-769.
23. Shumway R.H., Stoffer D.S. An approach to time series smoothing and forecasting using the EM algorithm. J. Time Ser. Anal. 3(4):1982;253-264.
24. R. Togneri, L. Deng, An EKF-based algorithm for learning statistical hidden dynamic model parameters for phonetic recognition, Proc. ICASSP'2001, to be published May 2001.