A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data Reuse
The principal issue in acoustic echo cancellation (AEC) is to estimate the impulse response between the loudspeaker and microphone of a hands-free communication device. This application can be addressed as a system identification problem, which can be solved by using an adaptive filter. The most com...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Algorithms |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4893/15/4/111 |
_version_ | 1797437252460085248 |
---|---|
author | Alexandru-George Rusu Constantin Paleologu Jacob Benesty Silviu Ciochină |
author_facet | Alexandru-George Rusu Constantin Paleologu Jacob Benesty Silviu Ciochină |
author_sort | Alexandru-George Rusu |
collection | DOAJ |
description | The principal issue in acoustic echo cancellation (AEC) is to estimate the impulse response between the loudspeaker and microphone of a hands-free communication device. This application can be addressed as a system identification problem, which can be solved by using an adaptive filter. The most common one for AEC is the normalized least-mean-square (NLMS) algorithm. It is known that the overall performance of this algorithm is controlled by the value of its normalized step size parameter. In order to obtain a proper compromise between the main performance criteria (e.g., convergence rate/tracking versus accuracy/robustness), this specific term of the NLMS algorithm can be further controlled and designed as a variable parameter. This represents the main motivation behind the development of variable step size algorithms. In this paper, we propose a variable step size NLMS (VSS-NLMS) algorithm that exploits the data reuse mechanism, which aims to improve the convergence rate/tracking of the algorithm by reusing the same set of data (i.e., the input and reference signals) several times. Nevertheless, we involved an equivalent version of the data reuse NLMS, which provides the convergence modes of the algorithm. Based on this approach, a sequence of normalized step sizes can be a priori scheduled, which is advantageous in terms of the computational complexity. The simulation results in the context of AEC supported the good performance features of the proposed VSS-NLMS algorithm. |
first_indexed | 2024-03-09T11:17:32Z |
format | Article |
id | doaj.art-b1eb2cb86d1e4b79ac865585336af3b2 |
institution | Directory Open Access Journal |
issn | 1999-4893 |
language | English |
last_indexed | 2024-03-09T11:17:32Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Algorithms |
spelling | doaj.art-b1eb2cb86d1e4b79ac865585336af3b22023-12-01T00:28:43ZengMDPI AGAlgorithms1999-48932022-03-0115411110.3390/a15040111A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data ReuseAlexandru-George Rusu0Constantin Paleologu1Jacob Benesty2Silviu Ciochină3Department of Telecommunications, University Politehnica of Bucharest, 060042 Bucharest, RomaniaDepartment of Telecommunications, University Politehnica of Bucharest, 060042 Bucharest, RomaniaINRS-EMT, University of Quebec, Montreal, QC H5A 1K6, CanadaDepartment of Telecommunications, University Politehnica of Bucharest, 060042 Bucharest, RomaniaThe principal issue in acoustic echo cancellation (AEC) is to estimate the impulse response between the loudspeaker and microphone of a hands-free communication device. This application can be addressed as a system identification problem, which can be solved by using an adaptive filter. The most common one for AEC is the normalized least-mean-square (NLMS) algorithm. It is known that the overall performance of this algorithm is controlled by the value of its normalized step size parameter. In order to obtain a proper compromise between the main performance criteria (e.g., convergence rate/tracking versus accuracy/robustness), this specific term of the NLMS algorithm can be further controlled and designed as a variable parameter. This represents the main motivation behind the development of variable step size algorithms. In this paper, we propose a variable step size NLMS (VSS-NLMS) algorithm that exploits the data reuse mechanism, which aims to improve the convergence rate/tracking of the algorithm by reusing the same set of data (i.e., the input and reference signals) several times. Nevertheless, we involved an equivalent version of the data reuse NLMS, which provides the convergence modes of the algorithm. Based on this approach, a sequence of normalized step sizes can be a priori scheduled, which is advantageous in terms of the computational complexity. The simulation results in the context of AEC supported the good performance features of the proposed VSS-NLMS algorithm.https://www.mdpi.com/1999-4893/15/4/111acoustic echo cancellation (AEC)adaptive filtersdata reusenormalized least-mean-square (NLMS) algorithmvariable step size (VSS) |
spellingShingle | Alexandru-George Rusu Constantin Paleologu Jacob Benesty Silviu Ciochină A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data Reuse Algorithms acoustic echo cancellation (AEC) adaptive filters data reuse normalized least-mean-square (NLMS) algorithm variable step size (VSS) |
title | A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data Reuse |
title_full | A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data Reuse |
title_fullStr | A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data Reuse |
title_full_unstemmed | A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data Reuse |
title_short | A Variable Step Size Normalized Least-Mean-Square Algorithm Based on Data Reuse |
title_sort | variable step size normalized least mean square algorithm based on data reuse |
topic | acoustic echo cancellation (AEC) adaptive filters data reuse normalized least-mean-square (NLMS) algorithm variable step size (VSS) |
url | https://www.mdpi.com/1999-4893/15/4/111 |
work_keys_str_mv | AT alexandrugeorgerusu avariablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse AT constantinpaleologu avariablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse AT jacobbenesty avariablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse AT silviuciochina avariablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse AT alexandrugeorgerusu variablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse AT constantinpaleologu variablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse AT jacobbenesty variablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse AT silviuciochina variablestepsizenormalizedleastmeansquarealgorithmbasedondatareuse |