PCMM-based feature compensation schemes using model interpolation and mixture sharing

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

Volumn 1, Issue , 2004, Pages

  Kim, Wooil ^a   Kwon, Ohil ^b   Ko, Hanseok ^a  

^a Korea University   (South Korea)

^b Hyundai Autonet Co Ltd   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC DISTORTION; COMPUTATIONAL COMPLEXITY; DATABASE SYSTEMS; FEATURE EXTRACTION; GAUSSIAN NOISE (ELECTRONIC); MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION;

MIXTURE SHARING; PARALLEL COMBINED MIXTURE MODEL (PCMM); SPEECH RECOGNITION SYSTEMS;

SPEECH RECOGNITION;

EID: 4544324741     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. X. Huang, A. Acero and H. Hon, Spoken Language Processing, Prentice Hall PTR, 2001.
2. M. J. F Gales and S. J. Young, "Robust Continuous Speech Recognition Using Parallel Model Combination," IEEE Trans. on Speech and Audio Processing, Vol.4, No.5, pp.352-359, Sep. 1996.
3. P. J. Moreno, B. Raj and R. M. Stern, "Data-driven Environmental Compensation for Speech Recognition: A Unified Approach," Speech Communication, Vol.24. No.4, pp.267-285, July 1998.
4. P. J. Moreno, Speech Recognition in Noisy Environments, PhD Thesis, Carnegie Mellon University, 1996.
5. W. Kim, S. Ahn and H. Ko, "Feature Compensation Scheme Based on Parallel Combined Mixture Model," Proc. Eurospeech2003, pp.677-680, Sep. 2003.
6. http://www.sitec.or.kr