We show that, given data from a mixture of k well-separated spherical Gaussians in Rd, a simple two-round variant of EM will, with high probability, learn the parameters of the Ga...
Background modeling and subtraction is a fundamental task in many computer vision and video processing applications. We present a novel probabilistic background modeling and subtr...
This paper proposes an interpolating extension to hidden Markov models (HMMs), which allows more accurate modeling of natural sounds sources. The model is able to produce observat...
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 ...