# Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3

arXiv: https://arxiv.org/abs/2306.09382 · HTML: https://mlsanity.com/paper/2306.09382/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 15 Jun 2023.

## Builds on (most cited first, 10 of 10)

- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [The 2018 Signal Separation Evaluation Campaign](https://mlsanity.com/paper/1804.06267/) (2018)
- [Music Demixing Challenge 2021](https://mlsanity.com/paper/2108.13559/) (2021)
- [KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing](https://mlsanity.com/paper/2111.12203/) (2021)
- [Channel-wise Subband Input for Better Voice and Accompaniment Separation on High Resolution Music](https://mlsanity.com/paper/2008.05216/) (2020)
- [CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet](https://mlsanity.com/paper/2112.04685/) (2021)
- [Improving singing voice separation using Deep U-Net and Wave-U-Net with data augmentation](https://mlsanity.com/paper/1903.01415/) (2019)

## Built on by (most cited first, 4 of 4)

- [A Two-Stage Band-Split Mamba-2 Network For Music Separation](https://mlsanity.com/paper/2409.06245/) (2024)
- [A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separation](https://mlsanity.com/paper/2602.21476/) (2026)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)
- [Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation](https://mlsanity.com/paper/2604.01120/) (2026)

## Abstract (arXiv)

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.