mlsanityData to 7 Oct 2026

Summary of The Inaugural Music Source Restoration Challenge

arXiv 2601.04343 ↗First posted 7 Jan 2026cs.SD cs.AI eess.AScited by 1

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

17 of 23 references.

References · 17

  1. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 707
  2. 2022High Fidelity Neural Audio Compressioncited by 673
  3. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  4. 2018Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Datasetcited by 215
  5. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  6. 2022Music Source Separation with Band-split RNNcited by 69
  7. 2016Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applicationscited by 60
  8. 2021Music Demixing Challenge 2021cited by 38
  9. 2023Moisesdb: A dataset for source separation beyond 4-stemscited by 37
  10. 2023Music Source Separation with Band-Split RoPE Transformercited by 36
  11. 2023Mel-Band RoFormer for Music Source Separationcited by 17
  12. 2023The Sound Demixing Challenge 2023 unicodex2013 Cinematic Demixing Trackcited by 11
5 more
  1. 2023Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)cited by 11
  2. 2023Benchmarks and leaderboards for sound demixing taskscited by 6
  3. 2025Zimtohrli: An Efficient Psychoacoustic Audio Similarity Metriccited by 6
  4. 2025Music Source Restorationcited by 5
  5. 2025MSRBench: A Benchmarking Dataset for Music Source Restorationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DTT-BSR+: A Generative-Regression Cascade for Music Source Restorationcited by 0