The existing blind source separation (BSS) architectures are more often than not based upon software and thus not suitable for direct implementation on hardware. Presented is a parallel algorithm and architecture for a BSS based on parallel architecture. The hardware testing performed with real world speech signals is found to be viable in terms of real time computation and separation ability.
Published in:
Electronics Letters
(Volume:40
,
Issue:
17
)
Date of Publication: 19 Aug. 2004