Improved model parameter compensation methods for noise-robust speech recognition

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

Volumn 1, Issue , 1998, Pages 561-564

  Chang, Y H ^a   Chung, Y J ^a   Park, S U ^a  

^a LGIC   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

BETTER PERFORMANCE; ENVIRONMENTAL VARIABLES; EXPECTATION-MAXIMIZATION ALGORITHMS; MIXTURE COMPONENTS; NOISE ROBUST SPEECH RECOGNITION; PARAMETER VARIABILITY; SPEAKER INDEPENDENTS; VECTOR TAYLOR SERIES;

ALGORITHMS; SIGNAL PROCESSING; SPEECH RECOGNITION;

ACOUSTIC NOISE;

EID: 0031619383     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1998.674492     Document Type: Conference Paper

References (7)

1. M. Gales and S. Young, "An improved approach to the hidden Markov model decomposition of speech and noise". in Proceedings oflCASSP, pp. 233-236, 1992.
2. M. Gales and S. Young, "Cepstral parameter compensation for HMM recognition". Speech Communication, no. 3, pp. 233-236, 1993.
3. L. R. Rabiner and B. H. Juang, "An Introduction to hidden Markov Models". IEEE ASSP Magazine, no. 1, pp. 4-16, Jan. 1986.
4. C. K. Un, D. Y. Kim, and Y. H. Chang, A Study on Noise-Robust Techniques for Speech Recognition. Final Report, KAIST, Dec. 1996.
5. I. J. Choi, O. W. Kwon, J. L. Park, D. Y. Kim, H. Y. Chung, C. K. Un, "Korean speech database for auto-interpretation", Proceedings of speech communication and signal processing workshop, pp. 287-290, 1994. (Edited by Korean)
6. P. Moreno, Speech Recognition in Noisy Environments. PhD thesis, Carnegie Mellon Univ., April 1996.
7. M. Gales, Model-based techniques for noise robust speech recognition. PhD thesis, Gonville and Caius College, Sep. 1995.