Summary of The Inaugural Music Source Restoration Challenge
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914239551111168 |
|---|---|
| author | Zang, Yongyi Hai, Jiarui Ge, Wanying Kong, Qiuqiang Dai, Zheqi Wang, Helin Mitsufuji, Yuki Plumbley, Mark D. |
| author_facet | Zang, Yongyi Hai, Jiarui Ge, Wanying Kong, Qiuqiang Dai, Zheqi Wang, Helin Mitsufuji, Yuki Plumbley, Mark D. |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04343 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Summary of The Inaugural Music Source Restoration Challenge Zang, Yongyi Hai, Jiarui Ge, Wanying Kong, Qiuqiang Dai, Zheqi Wang, Helin Mitsufuji, Yuki Plumbley, Mark D. Sound Artificial Intelligence Audio and Speech Processing 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/. |
| title | Summary of The Inaugural Music Source Restoration Challenge |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.04343 |