发表机构
Nanyang Technological University; Northwestern Polytechnical University; Zhejiang University（南洋理工大学; 西北工业大学; 浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对时变声学路径下主动噪声控制中元自适应滤波特征失配问题，提出耦合元自适应滤波方法，联合学习控制滤波器与路径跟踪，在实测路径上优于现有算法且泛化良好。
AI 中文摘要
元自适应滤波（Meta-AF）通过在整个在线自适应过程中采用学习型优化器，为手工设计的自适应滤波器更新提供了一种数据驱动的替代方案。然而，当Meta-AF用于主动噪声控制（ANC）时，时变声学路径仍然是一个主要挑战。特别是，物理信息优化器特征是利用次级路径估计构建的，当物理路径发生变化时，这些特征会变得不匹配，导致滤波器更新不准确和降噪性能下降。为解决这一问题，本文提出了一种耦合元自适应滤波主动噪声控制（CoMeta-AF-ANC）方法，该方法在闭环框架内应用元学习来联合学习控制滤波器自适应和声学路径跟踪。所提出的元门控联合路径识别器（MG-JPI）无需辅助噪声即可从可用的ANC信号中同时跟踪初级路径和次级路径，同时将更新的次级路径估计反馈回来以重建Meta-AF控制器特征。一种无延迟的双速率实现以帧速率执行学习自适应，同时在时域中以采样速率生成控制信号。使用实测头枕声学路径的评估表明，CoMeta-AF-ANC在跟踪时变声学路径方面优于代表性的ANC算法，同时在未见过的头部移动场景中保持更高的稳定性。它还对训练中未遇到的实际噪声具有良好的泛化能力。
英文摘要
Meta-adaptive filtering (Meta-AF) provides a data-driven alternative to hand-crafted adaptive filter updates by employing a learned optimizer throughout online adaptation. However, when Meta-AF is used for active noise control (ANC), time-varying acoustic paths remain a major challenge. In particular, the physics-informed optimizer features are constructed using a secondary path estimate and become mismatched when the physical path changes, leading to inaccurate filter updates and degraded noise reduction. To address this problem, this paper proposes a Coupled Meta-Adaptive Filtering Active Noise Control (CoMeta-AF-ANC) method, which applies meta-learning to jointly learn the control filter adaptation and acoustic path tracking within a closed-loop framework. The proposed Meta-Gated Joint Path Identifier (MG-JPI) simultaneously tracks the primary and secondary paths from the available ANC signals without auxiliary noise, while the updated secondary path estimate is fed back to reconstruct the Meta-AF controller features. A delayless dual-rate realization performs learned adaptation at the frame rate while generating the control signal at the sampling rate in the time domain. Evaluation using measured headrest acoustic paths shows that CoMeta-AF-ANC outperforms representative ANC algorithms in tracking time-varying acoustic paths, while maintaining higher stability across unseen head movement scenarios. It also generalizes well to real-world noises not encountered during training.
