Frequency domain correpondence for speaker normalization


Dynamic warping for pose-invariant face recognition


GMM chain model for speaker recognition


Segmental Rescoring framework for phoneme classification


Iterative Cohort modeling for speaker verification


Bandwise VQ for speaker model compression


Time Correlation Search for efficient speaker verification


Gaussian Tree Model for efficient speaker verification


Speech Segmentation based on Bayesin predictive principle


Multimodal person identification for CLEAR evaluation 2006


02/08/2007
© Ming Liu