Speaker: Wooil Kim
Title: Feature compensation method using parallel combination of Gaussian mixture model

Abstract:
This talk will discuss an effective feature compensation scheme based on the speech model 
in order to achieve robust speech recognition.  In the proposed method, the parallel model 
combination method is applied to estimation of noise-corrupted speech model.  Employing model 
combination method eliminates an additional training procedure and computational expense.  
It also brings an effective adaptation of noise model and more reliable estimation of the 
noisy-speech model.  In addition, another scheme will be introduced to cope with the 
time-varying background noise environment.  In this scheme, the interpolation method of the 
multiple mixture models is applied and a technique for mixture sharing is proposed for reducing 
the computational complex.  The performance is examined over Aurora 2.0 and speech corpus 
recorded while car-driving.  The experimental results indicate that the proposed schemes are 
effective in realizing robust speech.
[1] W. Kim, O. Kwon and H. Ko, "PCMM-based Feature Compensation Schemes Using Model 
    Interpolation and Mixture Sharing," ICASSP2004, pp. 989-992, May. 2004.
[2] W. Kim, S. Ahn and H. Ko, "Feature Compensation Scheme Based on Parallel Combined 
     Mixture Model," Eurospeech2003, pp. 677-680, Sep. 2003.

Bio:
Wooil Kim (http://ispl.korea.ac.kr/~wikim/ind_wikim.html)
Visiting Researcher, Robust Speech Recognition Group, ECE, CMU (advised by Prof. Richard Stern)
ISPL, ECE, Korea University (advised by Prof. Hanseok Ko)

2004-Present : Visiting researcher, ECE, CMU (KOSEF Post-doc. Program)
2003-2004 : Post-doc. BK21, Korea University
1998-2003 : EE, Korea University (Ph.D.)
1996-1998 : EE, Korea University (M.S.)
1992-1996 : EE, Korea University (B.S.)