Title :
Parallel LMS-based adaptive algorithms of echo cancellation
Author :
Dobrucki, Andrzej ; Bozejko, Wojciech ; Walczynski, Maciej
Author_Institution :
Dept. of Acoust. & Multimedia, Wroclaw Univ. of Technol., Wrocław, Poland
Abstract :
This paper deals with a number of parallel LMS family algorithms in the context of their use in the acoustic echo cancellation. The most complex parts of the LMS-based algorithms were determined and parallelized. A number of parallelization methods were designed taking under consideration varied types of architectures of modern concurrent computing environment, such as GPUs, clusters of workstations and cloud computing.
Keywords :
echo suppression; graphics processing units; least mean squares methods; parallel algorithms; GPU; acoustic echo cancellation; adaptive algorithms; cloud computing; concurrent computing environment; parallel LMS algorithms; parallelization method; workstation clusters; Computational modeling; Microphones; Phase change random access memory; Runtime; Speech; GPU; adaptive algorithms; echo cancellation; parallel algorithms;
Conference_Titel :
Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2014
Print_ISBN :
978-8-3620-6518-9
