Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.10256 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916000231849984 |
|---|---|
| author | Makris, Dimos Barják, András Kaliakatsos-Papakostas, Maximos |
| author_facet | Makris, Dimos Barják, András Kaliakatsos-Papakostas, Maximos |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10256 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Cold Diffusion Approach for Percussive Dereverberation Makris, Dimos Barják, András Kaliakatsos-Papakostas, Maximos Sound Artificial Intelligence 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. |
| title | A Cold Diffusion Approach for Percussive Dereverberation |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2605.10256 |