This paper introduces a dynamically regularized fast recursive least squares (DR-FRLS) adaptive filtering algorithm. Numerically stabilized FRLS algorithms exhibit reliable and fast convergence with low complexity even when the excitation signal is highly self-correlated. FRLS still suffers from instability, however, when the condition number of the implicit excitation sample covariance matrix is very high. DR-FRLS, overcomes this problem with a regularization process which only increases the computational complexity by 50%. The benefits of regularization include: (1) the ability to use small forgetting factors resulting in improved tracking ability and (2) better convergence over the standard regularization technique of noise injection. Also, DR-FRLS allows the degree of regularization to be modified quickly without restarting the algorithm. The application of DR-FRLS to stabilizing the fast affine projection (FAR) algorithm is also discussed.

Meeting Name

IEEE International Conference on Acoustics, Speech, and Signal Processing, 1996


Electrical and Computer Engineering

Keywords and Phrases

DR-FRLS; Acoustic Echo Cancellation; Acoustic Signal Processing; Adaptive Filtering Algorithm; Adaptive Filters; Adaptive Signal Processing; Computational Complexity; Condition Number; Dynamically Regularized Fast RLS; Echo Suppression; Excitation Sample Covariance Matrix; Fast Affine Projection Algorithm; Fast Convergence; Fast Recursive Least Squares; Filtering Theory; Instability; Least Squares Approximations; Noise Injection; Numerical Stability; Numerically Stabilized FRLS Algorithms; Recursive Filters; Regularization Process; Self Correlated Excitation Signal; Small Forgetting Factors; Tracking; Tracking Ability

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 1996 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link