Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing

TL;DR

This paper proposes an adaptive audio front-end using a neural controller to dynamically tune Per-Channel Energy Normalization, enhancing robustness across diverse acoustic environments.

Contribution

It introduces a novel adaptive paradigm with a neural controller that dynamically adjusts the front-end, improving robustness over fixed and traditional learnable front-ends.

Findings

Outperforms prior fixed and learnable front-ends in various tasks.

Enhances robustness in complex acoustic conditions.

Demonstrates effectiveness across multiple audio classification tasks.

Abstract

In audio signal processing, learnable front-ends have shown strong performance across diverse tasks by optimizing task-specific representation. However, their parameters remain fixed once trained, lacking flexibility during inference and limiting robustness under dynamic complex acoustic environments. In this paper, we introduce a novel adaptive paradigm for audio front-ends that replaces static parameterization with a closed-loop neural controller. Specifically, we simplify the learnable front-end LEAF architecture and integrate a neural controller for adaptive representation via dynamically tuning Per-Channel Energy Normalization. The neural controller leverages both the current and the buffered past subband energies to enable input-dependent adaptation during inference. Experimental results on multiple audio classification tasks demonstrate that the proposed adaptive front-end consistently outperforms prior fixed and learnable front-ends under both clean and complex acoustic conditions. These results highlight neural adaptability as a promising direction for the next generation of audio front-ends.