Stranded Gaussian mixture hidden Markov models for robust speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2012, Pages 4301-4304

  Zhao, Yong ^a   Juang, Biing Hwang ^a  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Dynamic Bayesian network; Gaussian mixture model; hidden Markov model; robust speech recognition

Indexed keywords

DISCRIMINATING POWER; DYNAMIC BAYESIAN NETWORKS; GAUSSIAN MIXTURE MODEL; GAUSSIAN MIXTURES; HETEROGENEOUS DATA SOURCES; MIXTURE COMPONENTS; MODELING TECHNIQUE; ROBUST SPEECH RECOGNITION;

HIDDEN MARKOV MODELS; SIGNAL PROCESSING; SPEECH RECOGNITION;

MIXTURES;

EID: 84867603321     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288870     Document Type: Conference Paper

References (9)

1. Y. Gong, "Stochastic trajectory modeling and sentence searching for continuous speech recognition," IEEE Trans. Speech Audio Process., vol. 5, no. 1, pp. 33-44, 1997.
2. C. J.Wellekens, "Explicit time correlation in hidden Markov models for speech recognition," in Proc. ICASSP, 1987, pp. 384-386.
3. J. A. Bilmes, "Graphical models and automatic speech recognition," in Mathematical foundations of speech and language processing. Springer-Verlag, New York, 2003.
4. P. Kenny, M. Lennig, and P. Mermelstein, "A linear predictive HMM for vector-valued observations with applications to speech recognition," IEEE Trans. Acoust., Speech, Signal Process., vol. 38, no. 2, pp. 220-225, Feb. 1990.
5. J. Su, H. Li, J. P. Haton, and K. T. Ng, "Speaker time-drifting adaptation using trajectory mixture hidden Markov models," in Proc. ICASSP, 1996, pp. 709-712.
6. F. Korkmazskiy, B. H. Juang, and F. K. Soong, "Generalized mixture of HMMs for continuous speech recognition," in Proc. ICASSP, 1997, pp. 1443-1446.
7. K. P. Murphy, Dynamic Bayesian networks: representation, inference and learning, Ph.D. thesis, Univ. Calif. Berkeley, 2002.
8. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, Feb. 1989.
9. H. G. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ISCA ITRW ASR, 2000, pp. 181-188.