A Cold Diffusion Approach for Percussive Dereverberation

TL;DR

This paper introduces a cold diffusion framework for dereverberating stereo drum signals, addressing the unique challenges of percussive audio and demonstrating superior performance over existing methods.

Contribution

It proposes a novel cold diffusion approach with two parameterizations and backbone architectures, specifically designed for percussive dereverberation.

Findings

Outperforms existing score-based and conditional diffusion baselines.

Effective on both synthetic and real reverberant drum recordings.

Demonstrates robustness in out-of-domain tests.

Abstract

Most recent advances in audio dereverberation focus almost exclusively on speech, leaving percussive and drum signals largely unexplored despite their importance in music production. Percussive dereverberation poses distinct challenges due to sharp transients and dense temporal structure. In this work, we propose a cold diffusion framework for dereverberating stereo drum stems (downmixes), modeling reverberation as a deterministic degradation process that progressively transforms anechoic signals into reverberant ones. We investigate two reverse-process parameterizations, Direct (next-state) and a Delta-normalized residual (velocity-style) prediction, and implement the framework using both a UNet and a diffusion Transformer backbone. The models are trained and evaluated on curated datasets comprising both acoustic and electronic drum recordings, with reverberation generated using a combination of synthetic and real room impulse responses. Extensive experiments on in-domain and fully out-of-domain test sets demonstrate that the proposed method consistently outperforms strong score-based and conditional diffusion baselines, evaluated using signal-based and perceptual metrics tailored to percussive audio.