Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.14356 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911388728819712 |
|---|---|
| author | Hernandez-Olivan, Carlos Koops, Hendrik Vincent Tan, Hao Hao Quinton, Elio |
| author_facet | Hernandez-Olivan, Carlos Koops, Hendrik Vincent Tan, Hao Hao Quinton, Elio |
| contents | Audio restoration consists in inverting degradations of a digital audio signal to recover what would have been the pristine quality signal before the degradation occurred. This is valuable in contexts such as archives of music recordings, particularly those of precious historical value, for which a clean version may have been lost or simply does not exist. Recent work applied generative models to audio restoration, showing promising improvement over previous methods, and opening the door to the ability to perform restoration operations that were not possible before. However, making these models finely controllable remains a challenge. In this paper, we propose an extension of FLowHigh and introduce the Dynamic Spectral Contour (DSC) as a control signal for bandwidth extension via classifier-free guidance. Our experiments show competitive model performance, and indicate that DSC is a promising feature to support fine-grained conditioning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14356 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Single-step Controllable Music Bandwidth Extension With Flow Matching Hernandez-Olivan, Carlos Koops, Hendrik Vincent Tan, Hao Hao Quinton, Elio Sound Audio restoration consists in inverting degradations of a digital audio signal to recover what would have been the pristine quality signal before the degradation occurred. This is valuable in contexts such as archives of music recordings, particularly those of precious historical value, for which a clean version may have been lost or simply does not exist. Recent work applied generative models to audio restoration, showing promising improvement over previous methods, and opening the door to the ability to perform restoration operations that were not possible before. However, making these models finely controllable remains a challenge. In this paper, we propose an extension of FLowHigh and introduce the Dynamic Spectral Contour (DSC) as a control signal for bandwidth extension via classifier-free guidance. Our experiments show competitive model performance, and indicate that DSC is a promising feature to support fine-grained conditioning. |
| title | Single-step Controllable Music Bandwidth Extension With Flow Matching |
| topic | Sound |
| url | https://arxiv.org/abs/2601.14356 |