In this paper we propose a novel order-recursive training algorithm for kernel-based discriminants which is computationally efficient. We integrate this method in a hybrid HMM-bas...
In this paper we address the application of single sensor source separation techniques to mixtures of speech and music. Three strategies for source modeling are presented, namely ...
This paper addresses one of the fundamental problems encountered in performance prediction for object recognition. In particular we address the problems related to estimation of s...
In this paper, we present a Gaussian mixture model based approach to capture the spatial characteristics of any target signal in a sensor network, and further propose a temporally...
Bayesian Kullback Ying—Yang dependence reduction system and theory is presented. Via stochastic approximation, implementable algorithms and criteria are given for parameter lear...