Low-cost design and implementation of an ICA-based blind source separation algorithm

Blind source separation (BSS) of independent sources from their convolutive mixtures is a problem in many real-world multi-sensor applications. In this paper, we propose a new low-cost design and implementation of an improved BSS algorithm for audio signals based on ICA (Independent Component Analysis) technique. It is performed by implementing non-causal filters instead of causal filters within the feedback network of the ICA based BSS method. Thereby, it reduces the required length of the unmixing filters considerably as well as providing better results and faster convergence compared to the case with the conventional causal filters. System level approach to the design of FPGA (field programmable gate array) prototype is adopted. Although FPGA does not offer an optimized hardware implementation when compared to ASIC (application specific integrated circuit), it allows short development time and enables verification of algorithms in hardware at a low cost. The hardware testing performed with real world audio signals is found successful.