Neural-Enhanced Dynamic Range Compression Inversion: A Hybrid Approach for Restoring Audio Dynamics

TL;DR

This paper presents a hybrid neural and model-based method for accurately inverting dynamic range compression in audio signals, improving restoration quality in music and speech applications.

Contribution

It introduces a novel hybrid approach combining neural networks with model-based inversion for robust DRC parameter estimation and audio restoration.

Findings

Outperforms state-of-the-art DRC inversion methods

Demonstrates robustness across music and speech datasets

Effectively estimates DRC parameters for high-quality audio restoration

Abstract

Dynamic Range Compression (DRC) is a widely used audio effect that adjusts signal dynamics for applications in music production, broadcasting, and speech processing. Inverting DRC is of broad importance for restoring the original dynamics, enabling remixing, and enhancing the overall audio quality. Existing DRC inversion methods either overlook key parameters or rely on precise parameter values, which can be challenging to estimate accurately. To address this limitation, we introduce a hybrid approach that combines model-based DRC inversion with neural networks to achieve robust DRC parameter estimation and audio restoration simultaneously. Our method uses tailored neural network architectures (classification and regression), which are then integrated into a model-based inversion framework to reconstruct the original signal. Experimental evaluations on various music and speech datasets confirm the effectiveness and robustness of our approach, outperforming several state-of-the-art techniques.