Summary of The Inaugural Music Source Restoration Challenge

TL;DR

The inaugural Music Source Restoration Challenge evaluated systems on their ability to recover original instrument stems from mixed and degraded audio, highlighting significant variation in restoration difficulty across instruments.

Contribution

This paper introduces the first MSR Challenge, providing datasets, evaluation protocols, and baselines for advancing music source restoration research.

Findings

Winning system achieved 4.46 dB Multi-Mel-SNR and 3.47 MOS-Overall.

Substantial variation in restoration difficulty across instruments.

The challenge fosters progress in music source restoration techniques.

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/.