Abstract
Blind source separation (BSS) has been widely utilized for recovering a set of source signals from their mixtures. When the mixture is convolutive, source separation can be solved in the frequency domain but involves several challenges including the scaling uncertainty and the permutation indeterminacy. This paper presents a sliding k-means algorithm to handle the permutation problem. Experiments were conducted by playing the source files to a pair of loudspeakers and obtaining the mixture by microphones. Objective indices are then defined to evaluate the separation performance based on the actual frequency responses. Results have shown that the standard k-means method alone can consistently achieve > 90.5% permutation accuracy in different parameter settings. After introducing the proposed sliding process, the permutation accuracy further rises. Compared to a previous de-permutation method [1], the present method has a more stable performance against parameter variations in terms of its permutation accuracy and signal-to-interference ratio (SIR).