Meta-Learning-Based Delayless Subband Adaptive Filter using Complex Self-Attention for Active Noise Control

TL;DR

This paper addresses active noise control under nonlinear and nonstationary conditions by reframing the problem as meta-learning and introducing a delayless subband architecture. A neural update rule implemented via a complex single-head attention RNN with learnable positional embedding drives the adaptive filter, while the delayless subband design and skip updating enable real-time operation. The method demonstrates superior NMSE and bandwidth attenuation across diverse noises and primary path changes, with robust generalization to unseen environments and system orders. The approaching framework offers practical impact for real-time ANC in devices with limited resources and varying acoustic paths, and points to future multi-channel implementations and computational accelerations.

Abstract

Active noise control typically employs adaptive filtering to generate secondary noise, where the least mean square algorithm is the most widely used. However, traditional updating rules are linear and exhibit limited effectiveness in addressing nonlinear environments and nonstationary noise. To tackle this challenge, we reformulate the active noise control problem as a meta-learning problem and propose a meta-learning-based delayless subband adaptive filter with deep neural networks. The core idea is to utilize a neural network as an adaptive algorithm that can adapt to different environments and types of noise. The neural network will train under noisy observations, implying that it recognizes the optimized updating rule without true labels. A single-headed attention recurrent neural network is devised with learnable feature embedding to update the adaptive filter weight efficiently, enabling accurate computation of the secondary source to attenuate the unwanted primary noise. In order to relax the time constraint on updating the adaptive filter weights, the delayless subband architecture is employed, which will allow the system to be updated less frequently as the downsampling factor increases. In addition, the delayless subband architecture does not introduce additional time delays in active noise control systems. A skip updating strategy is introduced to decrease the updating frequency further so that machines with limited resources have more possibility to board our meta-learning-based model. Extensive multi-condition training ensures generalization and robustness against various types of noise and environments. Simulation results demonstrate that our meta-learning-based model achieves superior noise reduction performance compared to traditional methods.

Figures (9)

• Figure 1: Diagram of single-channel feedforward ANC system
• Figure 2: Diagram of the ANC system with adaptive algorithm
• Figure 3: Diagram of modified delayless subband architecture with neural network module
• Figure 4: Proposed neural network architecture with self-attention
• Figure 5: Proposed ANR module with learnable positional embedding