Research Article
On the Regularization of the Memory-Improved Proportionate Affine Projection Algorithm
@INPROCEEDINGS{10.1007/978-3-319-92213-3_22, author={Roxana Mihăescu and Cristian Stanciu and Constantin Paleologu}, title={On the Regularization of the Memory-Improved Proportionate Affine Projection Algorithm}, proceedings={Future Access Enablers for Ubiquitous and Intelligent Infrastructures. Third International Conference, FABULOUS 2017, Bucharest, Romania, October 12-14, 2017, Proceedings}, proceedings_a={FABULOUS}, year={2018}, month={7}, keywords={Adaptive filters Echo cancellation Memory-improved affine projection algorithm (MIPAPA) Regularization}, doi={10.1007/978-3-319-92213-3_22} }- Roxana Mihăescu
Cristian Stanciu
Constantin Paleologu
Year: 2018
On the Regularization of the Memory-Improved Proportionate Affine Projection Algorithm
FABULOUS
Springer
DOI: 10.1007/978-3-319-92213-3_22
Abstract
In order to improve the performance of the conventional algorithms used for network and acoustic echo cancellation, we can exploit the sparseness character of the echo paths (i.e., a small percentage of the impulse response components have a significant magnitude while the rest are zero or small). In this paper, we consider the memory-improved proportionate affine projection algorithm (MIPAPA), which represents an appealing choice for echo cancellation. In this context, we focus on the regularization of this algorithm, relating the regularization parameter to the signal-to-noise ratio. In this way, the algorithm can operate properly in different noisy conditions. Simulation results indicate the good performance of the proposed solution.
