An algorithm for mixing matrix estimation in instantaneous blind source separation

• Main Authors: Reju, Vaninirappuputhenpurayil Gopalan, Koh, Soo Ngee, Soon, Ing Yann
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
• Online Access: https://hdl.handle.net/10356/94138; http://hdl.handle.net/10220/7013
• Institution: Nanyang Technological University

Sparsity of signals in the frequency domain is widely used for blind source separation (BSS) when the number of sources is more than the number of mixtures (underdetermined BSS). In this paper we propose a simple algorithm for detection of points in the Time-Frequency (TF) plane of the instantaneous mixtures where only single source contributions occur. Samples at these points in the TF plane can be used for the mixing matrix estimation. The proposed algorithm identifies the single-source points (SSPs) by comparing the absolute directions of the real and imaginary parts of the Fourier transform coefficient vectors of the mixed signals. Finally, the SSPs so obtained are clustered using the hierarchical clustering algorithm for the estimation of the mixing matrix. The proposed idea for the SSP identification is simpler than the previously reported algorithms.