Exploring the time-frequency microstructure of speech for blind source separation

This paper explores the different frequency contents in short time segments (temporal microstructure) of speech to identify the mixing matrix in blind source separation. We propose a new method based on the eigenspread in different frequency bands to identify the segments which contain only one of the mixtures. It is much simpler to accurately estimate the mixing matrices from these segments. This short-time subband analysis trains very fast and estimates reliably the column vectors of the linear mixture. Simulation results show that our proposed method outperforms the existing model-based and competitive learning approaches in the identification of the mixing matrix for both sensor-sufficient (as many sensors as sources) and sensor-deficient (less sensors than sources) cases.