Callaghan Innovation Research Papers

Back to Research Papers

TitleA GPU-accelerated real-time implementation of TRINICON-BSS for multiple separation units
Publication TypeConference Paper
Year of Publication2014
AuthorsAnderson, C.A., Meier S., Kellermann W., Teal P.D., and Poletti M.A.
Conference Name2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA 2014
Date Published2014
KeywordsAdaptive filtering, Blind source separation, Computational performance, Convolutive mixture, Double precision, Independent component analysis, Microphones, Parallel algorithms, Parallel architectures, Program processors, Real time control, Real-time implementations, Reference implementation, Second order statistics, Sensor array networks, Separation performance
AbstractIn this demonstration, a GPU-accelerated implementation of the second-order statistics version of the TRINICON (Triple-N independent component analysis for convolutive mixtures) blind source separation (BSS) algorithm is presented. The single-precision arithmetic separation performance is compared with a double-precision CPU (Central Processing Unit) reference implementation to establish the effect of parallel algorithms and the reduction of floatingpoint precision. Computational performance results are presented for a single 2-channel separation unit and multiple simultaneous 2-channel separation units to study the potential future use in a sensor array network with multiple 2-channel separation units. © 2014 IEEE.

Back to top