Similarity-Guided Diffusion for Long-Gap Music Inpainting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909798380863488 |
|---|---|
| author | Turland, Sean Moliner, Eloi Välimäki, Vesa |
| author_facet | Turland, Sean Moliner, Eloi Välimäki, Vesa |
| contents | Music inpainting aims to reconstruct missing segments of a corrupted recording. While diffusion-based generative models improve reconstruction for medium-length gaps, they often struggle to preserve musical plausibility over multi-second gaps. We introduce Similarity-Guided Diffusion Posterior Sampling (SimDPS), a hybrid method that combines diffusion-based inference with similarity search. Candidate segments are first retrieved from a corpus based on contextual similarity, then incorporated into a modified likelihood that guides the diffusion process toward contextually consistent reconstructions. Subjective evaluation on piano music inpainting with 2-s gaps shows that the proposed SimDPS method enhances perceptual plausibility compared to unguided diffusion and frequently outperforms similarity search alone when moderately similar candidates are available. These results demonstrate the potential of a hybrid similarity approach for diffusion-based audio enhancement with long gaps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16342 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Similarity-Guided Diffusion for Long-Gap Music Inpainting Turland, Sean Moliner, Eloi Välimäki, Vesa Audio and Speech Processing Machine Learning Sound Music inpainting aims to reconstruct missing segments of a corrupted recording. While diffusion-based generative models improve reconstruction for medium-length gaps, they often struggle to preserve musical plausibility over multi-second gaps. We introduce Similarity-Guided Diffusion Posterior Sampling (SimDPS), a hybrid method that combines diffusion-based inference with similarity search. Candidate segments are first retrieved from a corpus based on contextual similarity, then incorporated into a modified likelihood that guides the diffusion process toward contextually consistent reconstructions. Subjective evaluation on piano music inpainting with 2-s gaps shows that the proposed SimDPS method enhances perceptual plausibility compared to unguided diffusion and frequently outperforms similarity search alone when moderately similar candidates are available. These results demonstrate the potential of a hybrid similarity approach for diffusion-based audio enhancement with long gaps. |
| title | Similarity-Guided Diffusion for Long-Gap Music Inpainting |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2509.16342 |