Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3
This work addresses the problem of separating music sources for audio processing applications, representing an incremental improvement with specific gains in efficiency and performance.
The authors tackled music source separation by proposing TFC-TDF-UNet v3, a time-efficient model that achieved state-of-the-art results on the MUSDB benchmark, as part of their award-winning solutions for the Sound Demixing Challenge 2023.
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.