Summary of The Inaugural Music Source Restoration Challenge

Yongyi Zang, Jiarui Hai, Wanying Ge, Qiuqiang Kong, Zheqi Dai +3 more
1/7/2026
cs.SDcs.AIeess.AS

No confident code implementation found for this paper.

Abstract

Music Source Restoration (MSR) aims to recover original, unprocessed instrument stems from professionally mixed and degraded audio, requiring the reversal of both production effects and real-world degradations. We present the inaugural MSR Challenge, which features objective evaluation on studio-produced mixtures using Multi-Mel-SNR, Zimtohrli, and FAD-CLAP, alongside subjective evaluation on real-world degraded recordings. Five teams participated in the challenge. The winning system achieved 4.46 dB Multi-Mel-SNR and 3.47 MOS-Overall, corresponding to relative improvements of 91% and 18% over the second-place system, respectively. Per-stem analysis reveals substantial variation in restoration difficulty across instruments, with bass averaging 4.59 dB across all teams, while percussion averages only 0.29 dB. The dataset, evaluation protocols, and baselines are available at https://msrchallenge.com/.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Music Source Restoration

86% match1 repo312025

Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN

84% match2026

Apollo: Band-sequence Modeling for High-Quality Audio Restoration

78% match1 repo3922024

SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

78% match1 repo2002025

Benchmarks and leaderboards for sound demixing tasks

77% match1 repo8562023

The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss

77% match1 repo1942024

Cite this paper

@article{zang2026summary,
  title  = {Summary of The Inaugural Music Source Restoration Challenge},
  author = {Yongyi Zang and Jiarui Hai and Wanying Ge and Qiuqiang Kong and Zheqi Dai and Helin Wang and Yuki Mitsufuji and Mark D. Plumbley},
  year   = {2026},
  eprint = {2601.04343},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.04343v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.04343.svg)](https://codeofpaper.com/paper/2601.04343)

Discussion