SINGLE CHANNEL SOURCE SEPARATION USING STATIC AND DYNAMIC FEATURES IN THE POWER DOMAIN

In this paper we address the problem of separating the sound sources composing complex sound mixtures using a single microphone. The a-priori information of static and delta power of each source is represented by Gaussian mix-ture models (GMMs) and incorporated into a full posterior probability density function. We present a unified probabilis-tic framework that integrates the a-priori information of the power and the delta power of the sources and we derive a closed-form approximate minimum mean square error (MMSE) estimator of the audio sources. The experimental part evaluates our approach on mixtures of real environ-mental sounds in scenarios that involve speakers talking in a music background. Comprehensive experiments clarify the importance of incorporating delta in the separation process by presenting separation results using the static only and the joint static and delta a-priori models. 1