Co-Initialization of Control Filter and Secondary Path via Meta-Learning for Active Noise Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Ziyi, Rao, Li, Luo, Zhengding, Shi, Dongyuan, Huang, Qirui, Gan, Woon-Seng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911387122401280
author Yang, Ziyi
Rao, Li
Luo, Zhengding
Shi, Dongyuan
Huang, Qirui
Gan, Woon-Seng
author_facet Yang, Ziyi
Rao, Li
Luo, Zhengding
Shi, Dongyuan
Huang, Qirui
Gan, Woon-Seng
contents Active noise control (ANC) must adapt quickly when the acoustic environment changes, yet early performance is largely dictated by initialization. We address this with a Model-Agnostic Meta-Learning (MAML) co-initialization that jointly sets the control filter and the secondary-path model for FxLMS-based ANC while keeping the runtime algorithm unchanged. The initializer is pre-trained on a small set of measured paths using short two-phase inner loops that mimic identification followed by residual-noise reduction, and is applied by simply setting the learned initial coefficients. In an online secondary path modeling FxLMS testbed, it yields lower early-stage error, shorter time-to-target, reduced auxiliary-noise energy, and faster recovery after path changes than a baseline without re-initialization. The method provides a simple fast start for feedforward ANC under environment changes, requiring a small set of paths to pre-train.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13849
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Co-Initialization of Control Filter and Secondary Path via Meta-Learning for Active Noise Control
Yang, Ziyi
Rao, Li
Luo, Zhengding
Shi, Dongyuan
Huang, Qirui
Gan, Woon-Seng
Audio and Speech Processing
Machine Learning
Signal Processing
Active noise control (ANC) must adapt quickly when the acoustic environment changes, yet early performance is largely dictated by initialization. We address this with a Model-Agnostic Meta-Learning (MAML) co-initialization that jointly sets the control filter and the secondary-path model for FxLMS-based ANC while keeping the runtime algorithm unchanged. The initializer is pre-trained on a small set of measured paths using short two-phase inner loops that mimic identification followed by residual-noise reduction, and is applied by simply setting the learned initial coefficients. In an online secondary path modeling FxLMS testbed, it yields lower early-stage error, shorter time-to-target, reduced auxiliary-noise energy, and faster recovery after path changes than a baseline without re-initialization. The method provides a simple fast start for feedforward ANC under environment changes, requiring a small set of paths to pre-train.
title Co-Initialization of Control Filter and Secondary Path via Meta-Learning for Active Noise Control
topic Audio and Speech Processing
Machine Learning
Signal Processing
url https://arxiv.org/abs/2601.13849