Directional Selective Fixed-Filter Active Noise Control Based on a Convolutional Neural Network in Reverberant Environments

2025-10-22

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference

AI Summary

This work proposes a directional selective fixed-filter active noise control (ANC) method based on convolutional neural networks (CNNs) to address the performance limitations of conventional ANC approaches in reverberant environments, which typically neglect directional information of noise sources. By integrating direction-of-arrival (DOA) estimation—specifically azimuth and elevation angles—into a selective fixed-filter framework, the proposed method overcomes the restrictive free-field assumption commonly adopted in traditional ANC systems. Leveraging multi-channel reference signals, the CNN jointly estimates the DOA of noise sources and dynamically selects the optimal fixed filter accordingly. Experimental results demonstrate that, compared to conventional adaptive algorithms, the proposed approach achieves faster response times and superior noise reduction performance under reverberant conditions.

Technology Category

• Machine Learning: Active Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Selective fixed-filter active noise control (SFANC) is a novel approach capable of mitigating noise with varying frequency characteristics. It offers faster response and greater computational efficiency compared to traditional adaptive algorithms. However, spatial factors-particularly the influence of the noise source location-are often overlooked. Some existing studies have explored the impact of the direction-of-arrival (DoA) of the noise source on ANC performance, but they are mostly limited to free-field conditions and do not consider the more complex indoor reverberant environments. To address this gap, this paper proposes a learning-based directional SFANC method that incorporates the DoA of the noise source in reverberant environments. In this framework, multiple reference signals are processed by a convolutional neural network (CNN) to estimate the azimuth and elevation angles of the noise source, as well as to identify the most appropriate control filter for effective noise cancellation. Compared to traditional adaptive algorithms, the proposed approach achieves superior noise reduction with shorter response times, even in the presence of reverberations.

Problem

• Directional Selective Fixed-Filter ANC
• Direction-of-Arrival
• Reverberant Environments
• Active Noise Control
• Spatial Factors

Innovation

• Directional Selective Fixed-Filter ANC
• Convolutional Neural Network
• Direction-of-Arrival Estimation
• Reverberant Environments
• Active Noise Control