Adaptive signal processing, an important branch in the Signal and Information Processing field, is widely used in the signal processing of digital communication. This paper is devoted to the study of an adaptive filtering algorithm by using modified decorrelation. The structure and theoretic analysis of this algorithm is presented. And its optimal weight vector is the solution of generalized Wiener-Hopf equation. The convergence speed and the stable misadjustment of this algorithm are compared with the algorithm in reference [7] for various nonnegative constants for processing uncorrelated signals. In computer simulations, adaptive echo canceller is used to evaluate the performances of this algorithm, the algorithm in reference [7] and DCR-LMS algorithm. Experimental results indicate that the improved algorithm performs best compared with the other two algorithms for processing strong correlated signals.
[1]
Hiroshi Yasukawa,et al.
An acoustic echo canceller using subband sampling and decorrelation methods
,
1993,
IEEE Trans. Signal Process..
[2]
J. F. Doherty,et al.
A robust echo canceler for acoustic environments
,
1997
.
[3]
Kazuhiko Ozeki,et al.
An adaptive filtering algorithm using an orthogonal projection to an affine subspace and its properties
,
1984
.
[4]
Richard D. Gitlin,et al.
The Effects of Large Interference on the Tracking Capability of Digitally Implemented Echo Cancellers
,
1978,
IEEE Trans. Commun..
[5]
邵世煌,et al.
Study of Variable Step Size LMS Adaptive Algorithm Based on Variable Region
,
2006
.
[6]
B. Anderson,et al.
Performance of adaptive estimation algorithms in dependent random environments
,
1980
.