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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meng, Hanyu, Sethu, Vidhyasaharan, Ambikairajah, Eliathamby, Zhang, Qiquan, Li, Haizhou
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911404442779648
author Meng, Hanyu
Sethu, Vidhyasaharan
Ambikairajah, Eliathamby
Zhang, Qiquan
Li, Haizhou
author_facet Meng, Hanyu
Sethu, Vidhyasaharan
Ambikairajah, Eliathamby
Zhang, Qiquan
Li, Haizhou
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18206
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing
Meng, Hanyu
Sethu, Vidhyasaharan
Ambikairajah, Eliathamby
Zhang, Qiquan
Li, Haizhou
Audio and Speech Processing
Sound
Signal Processing
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.
title Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing
topic Audio and Speech Processing
Sound
Signal Processing
url https://arxiv.org/abs/2510.18206