A statistical model based residual echo suppression

Improved Global Soft Decision Using Smoothed Global Likelihood Ratio For Speech Enhancement

Voice activity detection based on a family of parametric distributions

Feature compensation incorporating modeling error statistics

Multiple statistical models for soft decision in noisy speech enhancement

Feature compensation with model-based estimation for noise masking

A new structural approach in system identification with generalized analysis-by-synthesis for robust speech coding

Signal modification for ADPCM based on analysis-by-synthesis framework

Voice activity detection based on multiple statistical models

Automatic speech segmentation based on boundary-type candidate selection