Year: 2025
Type: preprint
Abstract: Real-world audio is often degraded by numerous factors. This work presents an audio restoration model tailored for high-res music at 44.1kHz. Our model, Audio-to-Audio Schrödinger Bridges (A2SB), is capable of both bandwidth extension (predicting high-frequency components) and inpainting (re-generating missing segments). Critically, A2SB is end-to-end requiring no vocoder to predict waveform outputs, able to restore hour-long audio inputs, and trained on permissively licensed music data. A2SB is capable of achieving state-of-the-art band-width extension and inpainting quality on several out-of-distribution music test sets.
Source: arXiv (Cornell University)
Authors: Kong, Zhifeng, Shih, Kevin J, Nie, Weili, Vahdat, Arash, Lee, Sang-gil, Santos, Joao Felipe, Jukic, Ante, Valle, Rafael, Catanzaro, Bryan
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4406735048