A new variable step size LMS algorithm with application to active noise control

Author

Wang, Yue ; Zhang, Chun ; Wang, Zhihua

Author_Institution

Dept. of Electron. Eng., Tsinghua Univ., Beijing, China

Volume

5

fYear

2003

fDate

6-10 April 2003

Abstract

A new adaptive step size adjustment least mean square (LMS) algorithm is presented. The proposed algorithm modifies the existing LMS using the estimated output error as an important component for the modification of the step size. Experiment results demonstrate that application of the new algorithm leads to a significant gain in SNR (signal-to-noise ratio), thus visibly reduces the output error and greatly improves the convergence speed in the context of adaptive active noise cancellation.

Keywords

acoustic noise; acoustic signal processing; active noise control; adaptive filters; adaptive signal processing; convergence of numerical methods; least mean squares methods; parameter estimation; SNR; active noise cancellation; active noise control; adaptive LMS algorithm; adaptive filtering; convergence speed; output error estimation; signal-to-noise ratio; step size adjustment; Active noise reduction; Adaptive algorithm; Adaptive filters; Convergence; Electric variables control; Least squares approximation; Signal to noise ratio; Size control; Stability; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1200034

Filename

1200034