Home // International Journal On Advances in Systems and Measurements, volume 10, numbers 3 and 4, 2017 // View article

Insights on a Low-Cost Recursive Least-Squares Algorithm for Adaptive Noise Cancellation

Authors:
Roxana Mihăescu
Cristian Lucian Stanciu
Cristian Anghel
Lucian Stanciu

Keywords: adaptive noise cancellation; recursive leastsquares; dichotomous coordinate descent

Abstract:
Adaptive Noise Cancellation (ANC) belongs to the interference cancellation class. It employs an adaptive filter to estimate a perturbation signal, which corrupts a primary acoustic source. In most of the corresponding applications, the goal is to imitate an original speech signal. This paper proposes the use of a low-complexity recursive least-squares (RLS) adaptive algorithm for the ANC procedure. The combination between the RLS method and the dichotomous coordinate descent (DCD) iterations offers good performance with acceptable arithmetic costs. Simulation results are provided in order to demonstrate the validity of the ANC system based on the RLS-DCD adaptive algorithm.

Pages: 150 to 157

Copyright: Copyright (c) to authors, 2017. Used with permission.

Publication date: December 31, 2017

Published in: journal

ISSN: 1942-261x