.png){kind=icon}
.png){kind=icon}
Return
Total Least Squares Normalized Subband Adaptive Filter Algorithm for Noisy Input
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSII.2021.3133460.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Subband adaptive filter has been widely applied to process correlated input signals due to its decorrelation property. However, the performance of the subband adaptive filter algorithm will be drastically degraded in the case of both the input and output signals are contaminated with noise. To tackle this problem, this brief proposes a total least squares normalized subband adaptive filter (TLS-NSAF) algorithm,which is different from bias-compensated schemes. The proposed algorithm is derived by employing the Rayleigh quotient as the cost function and the gradient steepest descent method. The local mean stability and computational complexity of the proposed algorithm are also analyzed. Simulation results demonstrate that the TLS-NSAF algorithm has better performance in comparison with previous algorithms.
Keywords:
Signal processing algorithms
Convergence
Filtering algorithms
Adaptive filters
Adaptation models
Computational modeling
Computational complexity
Correlated input
errors-in-variables model
subband adaptive filter
total least squares
Journal
I
IF:
4.9
Papers:
8.8K
Citations:
2.5W