Single-step Controllable Music Bandwidth Extension With Flow Matching
Carlos Hernandez-Olivan, Hendrik Vincent Koops, Hao Hao Tan, Elio Quinton

TL;DR
This paper introduces a novel method for controllable audio bandwidth extension using flow matching and a new control signal, enabling more precise restoration of degraded music recordings.
Contribution
It extends existing flow-based models with a dynamic spectral contour control, enhancing fine-grained controllability in audio restoration tasks.
Findings
Competitive model performance demonstrated
DSC effectively supports fine-grained conditioning
Improves controllability in audio bandwidth extension
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMusic and Audio Processing · Speech and Audio Processing · Generative Adversarial Networks and Image Synthesis
