SOTAVerified

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.

Reproduce

Code

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

DatasetModelMetricClaimedVerifiedStatus
MUSDB18TFC-TDF-UNet (v3)SDR (avg)8.34Unverified
MUSDB18-HQTFC-TDF-UNet (v3)SDR (avg)8.34Unverified

Reproductions