# End-to-End Historical Music Restoration in Latent Space

arXiv: https://arxiv.org/abs/2610.00607 · HTML: https://mlsanity.com/paper/2610.00607/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Stable Audio Open](https://mlsanity.com/paper/2407.14358/) (2024)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications](https://mlsanity.com/paper/1612.08727/) (2016)
- [Nonlinear System Identification: A User-Oriented Roadmap](https://mlsanity.com/paper/1902.00683/) (2019)
- [NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling](https://mlsanity.com/paper/2104.02321/) (2021)
- [AudioSR: Versatile Audio Super-resolution at Scale](https://mlsanity.com/paper/2309.07314/) (2023)
- [Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach](https://mlsanity.com/paper/2306.01433/) (2023)
- [Aligning Text-to-Music Evaluation with Human Preferences](https://mlsanity.com/paper/2503.16669/) (2025)
- [FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching](https://mlsanity.com/paper/2501.04926/) (2025)
- [A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordings](https://mlsanity.com/paper/2202.08702/) (2022)
- [BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networks](https://mlsanity.com/paper/2204.06478/) (2022)
- [A Diffusion-Based Generative Equalizer for Music Restoration](https://mlsanity.com/paper/2403.18636/) (2024)
- [A2SB: Audio-to-Audio Schrodinger Bridges](https://mlsanity.com/paper/2501.11311/) (2025)
- [Learning to Denoise Historical Music](https://mlsanity.com/paper/2008.02027/) (2020)
- [CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio](https://mlsanity.com/paper/2509.09836/) (2025)
- [Fx-Encoder++: Extracting Instrument-Wise Audio Effects Representations from Mixtures](https://mlsanity.com/paper/2507.02273/) (2025)
- [Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approaches](https://mlsanity.com/paper/2504.04751/) (2025)
- [SAGA-SR: Semantically and Acoustically Guided Audio Super-Resolution](https://mlsanity.com/paper/2509.24924/) (2025)
- [SAME: A Semantically-Aligned Music Autoencoder](https://mlsanity.com/paper/2605.18613/) (2026)
- [The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval](https://mlsanity.com/paper/2511.21247/) (2025)
- [LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matching](https://mlsanity.com/paper/2604.09188/) (2026)

## Abstract (arXiv)

Historical music restoration (HMR) has almost exclusively focused on constrained problems such as Super-Resolution or the restoration of solo pieces, under-exploring the general task of restoring orchestral historical music, which has multiple instruments. This under-exploration is largely because the HMR domain, early-20th-century recordings, has no pre-degradation ground-truth pairs, making the restoration task unsupervised and more challenging. This paper presents a supervised end-to-end orchestral HMR benchmark by exploring both the synthetic degradation functions and the end-to-end generative deep-learning restoration methods. We simulate the historical recording degradation chain more faithfully than prior work, which makes orchestral restoration into a tractable supervised problem. A latent flow-matching model trained on the resulting synthetic pairs outperforms existing HMR baselines on intrusive, non-intrusive, and subjective evaluations. We also curate and release a 9.3-hour license-free, unpaired, historical classical-music test set, along with code and audio demos.