Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3
2023-06-15Code Available1· sign in to hype
Minseok Kim, Jun Hyung Lee, Soonyoung Jung
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/kuielab/sdx23OfficialIn paperpytorch★ 95
Abstract
In this report, we present our award-winning solutions for the Music Demixing Track of Sound Demixing Challenge 2023. First, we propose TFC-TDF-UNet v3, a time-efficient music source separation model that achieves state-of-the-art results on the MUSDB benchmark. We then give full details regarding our solutions for each Leaderboard, including a loss masking approach for noise-robust training. Code for reproducing model training and final submissions is available at github.com/kuielab/sdx23.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| MUSDB18 | TFC-TDF-UNet (v3) | SDR (avg) | 8.34 | — | Unverified |
| MUSDB18-HQ | TFC-TDF-UNet (v3) | SDR (avg) | 8.34 | — | Unverified |