Title :
Improvement of the mu-law proportionate NLMS algorithm
Author :
Liu, Ligang ; Fukumoto, Masahiro ; Zhang, Shiyong
Author_Institution :
Dept. of Comput. & Inf. Technol., Fudan Univ., Shanghai, China
Abstract :
The MPNLMS algorithm is preferred to identify the sparse impulse responses. In this paper, we present two strategies to improve it. We first establish a convergence criterion for it, which is suitable to achieve faster convergence speed in various environments with different noise level. Then we propose a new segment function to refine its original definition to improve the computation efficient SPNLMS algorithm. Simulation results verify the effectiveness of the proposed approaches.
Keywords :
filtering theory; least mean squares methods; Mu-law proportionate NLMS algorithm; SPNLMS algorithm; noise level; segment function; sparse impulse responses; Adaptive algorithm; Adaptive filters; Computational complexity; Computational modeling; Convergence; Information systems; Information technology; Noise level; Steady-state; Systems engineering and theory;
Conference_Titel :
Circuits and Systems, 2009. ISCAS 2009. IEEE International Symposium on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-3827-3
Electronic_ISBN :
978-1-4244-3828-0
DOI :
10.1109/ISCAS.2009.5118195
