H. Jeong and Y. Kim (Korea)
Blind source separation(BSS), Independent componentanalysis(ICA), VLSI
Blind Source Separation of independent sources from their convolutive mixtures is a problem in many real-world multi-sensor applications. However, the existing BSS ar chitectures are more often than not based upon software and thus not suitable for direct implementation on hard ware. In this paper, we present a parallel algorithm and architecture for a BSS based on systolic architecture. The hardware testing performed with real world speech signals is found to be viable in terms of real time computation and separation ability.
Important Links:
Go Back