Discriminative semi-parametric trajectory model for speech recognition

Computer Speech and Language

Volumn 21, Issue 4, 2007, Pages 669-687

  Sim, K C ^a   Gales, M J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Discriminative training; Minimum phone error; Speech recognition; Trajectory model

Indexed keywords

BENCHMARKING; COVARIANCE MATRIX; GAUSSIAN DISTRIBUTION; PARAMETER ESTIMATION; SPEECH RECOGNITION; TIME VARYING SYSTEMS;

DISCRIMINATIVE TRAINING; MINIMUM PHONE ERROR (MPE); TRAJECTORY MODELLING;

HIDDEN MARKOV MODELS;

EID: 34249951707     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2007.03.004     Document Type: Article

References (23)

1. Bilmes, J.A.,1999. Buried Markov models for speech recognition. In: Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing, pp. 713-716.
2. Evermann, G., Woodland, P.C., 2000. Posterior probability decoding, confidence estimation and system combination. In: Proceedings of the Speech Transcription Workshop.
3. Gales, M.J.F., 1997. Maximum likelihood linear transformations for HMM-based speech recognition. Technical Report CUED/F-INFENG/TR291, Cambridge University, (via anonymous) .
4. Gales M.J.F., and Woodland P.C. Mean and variance adaptation within the MLLR framework. Computer Speech and Languages 10 (1996) 249-264
5. Gales, M.J.F., Jia, B., Liu, X., Sim, K.C., Woodland, P.C., Yu, K., 2005. Development of the CUHTK 2004 RT04f mandarin conversational telephone speech transcription system. In: Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing, March 2005, pp. 861-864.
6. Hermansky H. Perceptual linear predictive (PLP) analysis of speech. Journal of the Acoustical Society of America 87 4 (1990) 1738-1752
7. Huang B.J., Levinson S.E., and Sondhi M.M. Maximum likelihood estimation for multivariate mixture observations of Markov chains. IEEE Transactions on Information Theory IT-32 March (1986) 307-309
8. Kumar, N., 1997. Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition. PhD Thesis, Johns Hopkins University.
9. Legetter C.J., and Woodland P.C. Maximum likelihood linear regression speaker adaptation of continuous density HMMs. Computer Speech and Languages (1997)
10. Mangu, L., Brill, E., Stolcke, A., 1999. Finding consensus among words: lattice-based word error minimization. In: Proceedings of the European Conference on Speech Communication and Technology.
11. Ostendorf M., and Roukos S. A stochastic segment model for phoneme-based continuous speech recognition. IEEE Transactions on Acoustics Speech and Signal Processing 37 12 (1989) 1857-1869
12. Ostendorf M., Digalakis V., and Kimball O. From HMM's to segment models: a unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing 4 5 (1996) 360-378
13. Povey, D., 2003. Discriminative training for large vocabulary speech recognition. PhD Thesis, Cambridge University.
14. Povey, D. 2005. Improvements to fMPE for discriminative training of features. In: Proceedings of the Interspeech, September.
15. Povey, D., Woodland, P.C., 2002. Minimum phone error and I-smoothing for improved discriminative training. In: Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing.
16. Povey, D., Kingsbury, B., Mangu, L., Saon, G., Soltau, H., Zweig, G., 2005. fMPE: Discriminatively trained features for speech recognition. In: Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing.
17. Rabiner, L.A., 1989. A tutorial on hidden Markov models and selective applications in speech recognition. In: Proceedings of the IEEE, February 1989, vol. 77, pp. 257-286.
18. Rosti, A-V.I., Gales, M.J.F. Switching linear dynamical systems for speech recognition. Technical Report CUED/F-INFENG/TR461, Cambridge University, 2003. (via anonymous) .
19. Sim, K.C., Gales, M.J.F. 2005. Temporally varying model parameters for large vocabulary continuous speech recognition. In: Proceedings of the Interspeech, September 2005.
20. Tokuda, K., Zen, H., Kitamura, T. 2003. Trajectory modeling based on HMMs with the explicit relationship between static and dynamic features. In: Proceedings of the European Conference on Speech and Communication Technology, pp. 865-868.
21. Tokuda, K., Zen, H., Kitamura, T. 2004. Reformulating the HMM as a trajectory model. In: Proceedings of Beyond HMM - Workshop on Statistical Modeling Approach for Speech Recognition.
22. Wellekens, C.J., 1987. Explicit time correlation in hidden Markov models for speech recognition. In: Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing, pp. 384-386.
23. Woodland, P.C. 1992. Hidden Markov models using vector linear prediction and discriminative output distributions. In: Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing, vol. 1, pp. 509-512.