Transferable Selective Virtual Sensing Active Noise Control Technique Based on Metric Learning

TL;DR

This paper introduces a transfer learning approach using metric learning to enable CNN-based virtual sensing in active noise control systems, allowing direct application to new systems and unseen noise types without retraining.

Contribution

It proposes a novel Transferable Selective Virtual Sensing method that leverages metric learning to make CNN models adaptable across different ANC systems and noise conditions.

Findings

Effective in attenuating broadband noises

Handles unseen noise types successfully

Eliminates need for retraining CNN models

Abstract

Virtual sensing (VS) technology enables active noise control (ANC) systems to attenuate noise at virtual locations distant from the physical error microphones. Appropriate auxiliary filters (AF) can significantly enhance the effectiveness of VS approaches. The selection of appropriate AF for various types of noise can be automatically achieved using convolutional neural networks (CNNs). However, training the CNN model for different ANC systems is often labour-intensive and time-consuming. To tackle this problem, we propose a novel method, Transferable Selective VS, by integrating metric-learning technology into CNN-based VS approaches. The Transferable Selective VS method allows a pre-trained CNN to be applied directly to new ANC systems without requiring retraining, and it can handle unseen noise types. Numerical simulations demonstrate the effectiveness of the proposed method in attenuating sudden-varying broadband noises and real-world noises.