Fast Adaptive Active Noise Control Based on Modified Model-Agnostic Meta-Learning Algorithm

With the advent of efficient low-cost processors and electroacoustic components, there is renewed interest in the practical implementation of active noise control (ANC). However, the slow convergence of conventional adaptive algorithms deployed in ANC restricts its handling of typical amplitude-vary...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters Vol. 28; pp. 593 - 597
Main Authors: Shi, Dongyuan, Gan, Woon-Seng, Lam, Bhan, Ooi, Kenneth
Format: Journal Article
Language:English
Published: New York IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Acceleration
Active noise control
Adaptation models
Adaptive algorithms
Adaptive control
Adaptive filters
Adaptive systems
Amplitudes
control filter initialization
Convergence
Cost function
fast adaptation
FxLMS
LF noise
Machine learning
Mathematical models
model-agnostic meta-learning
Noise control
Noise measurement
Signal processing algorithms
ISSN:1070-9908, 1558-2361
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the advent of efficient low-cost processors and electroacoustic components, there is renewed interest in the practical implementation of active noise control (ANC). However, the slow convergence of conventional adaptive algorithms deployed in ANC restricts its handling of typical amplitude-varying noise. Hence, we proposed a modified model-agnostic, meta-learning (MAML) strategy to obtain an initial control filter, which accelerates an adaptive algorithm's convergence when dealing with different types of amplitude-varying low-frequency noise. Numerical simulations with measured paths and real noise sources demonstrate its convergence acceleration efficacy in practical scenarios.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2021.3064756