| Hybrid Transformers for Music Source Separation | ✓ Link | 9.20 | 9.37 | 10.83 | 10.47 | 6.41 | Sparse HT Demucs (fine tuned) | 2022-11-15 |
| Hybrid Transformers for Music Source Separation | ✓ Link | 9.00 | 9.20 | 10.08 | 9.78 | 6.42 | Hybrid Transformer Demucs (f.t.) | 2022-11-15 |
| Music Source Separation with Band-split RNN | ✓ Link | 8.97 | 10.47 | 10.15 | 8.16 | 7.08 | Band-Split RNN (semi-sup.) | 2022-09-30 |
| Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3 | ✓ Link | 8.34 | 9.59 | 8.44 | 8.45 | 6.86 | TFC-TDF-UNet (v3) | 2023-06-15 |
| Music Source Separation with Band-split RNN | ✓ Link | 8.23 | 10.21 | 8.58 | 7.51 | 6.62 | Band-Split RNN | 2022-09-30 |
| Hybrid Spectrogram and Waveform Source Separation | ✓ Link | 7.72 | 8.04 | 8.58 | 8.67 | 5.59 | Hybrid Demucs | 2021-11-05 |
| KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing | ✓ Link | 7.54 | 9.00 | 7.33 | 7.86 | 5.95 | KUIELab-MDX-Net | 2021-11-24 |
| Hierarchic Temporal Convolutional Network With Cross-Domain Encoder for Music Source Separation | | 6.89 | 7.37 | 7.33 | 7.92 | 4.92 | CDE-HTCN | 2022-06-30 |
| An Efficient Short-Time Discrete Cosine Transform and Attentive MultiResUNet Framework for Music Source Separation | ✓ Link | 6.81 | 8.57 | 7.63 | 5.88 | 5.14 | Attentive-MultiResUNet | 2022-11-14 |
| Music Source Separation in the Waveform Domain | ✓ Link | 6.79 | 7.29 | 7.58 | 7.60 | 4.69 | DEMUCS (extra) | 2019-11-27 |
| CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet | ✓ Link | 6.77 | 8.92 | 6.38 | 5.93 | 5.84 | CWS-PResUNet | 2021-12-09 |
| D3Net: Densely connected multidilated DenseNet for music source separation | ✓ Link | 6.68 | 7.80 | 7.36 | 6.20 | 5.37 | D3Net | 2020-10-05 |
| Contrastive Learning based Deep Latent Masking for Music Source Separation | | 6.47 | 6.91 | 7.05 | 7.29 | 4.62 | DLMNet | 2023-08-20 |
| Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation | ✓ Link | 6.32 | 6.74 | 7.11 | 7.00 | | Conv-TasNet (extra) | 2018-09-20 |
| Open-Unmix - A Reference Implementation for Music Source Separation | ✓ Link | 6.316 | 7.213 | 7.148 | 6.015 | 4.889 | UMXL | 2019-09-08 |
| Music Source Separation in the Waveform Domain | ✓ Link | 6.28 | 6.84 | 6.86 | 7.01 | 4.42 | DEMUCS | 2019-11-27 |
| MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation | ✓ Link | 6.04 | 7.16 | 6.81 | 5.40 | 4.80 | TAK2 | 2018-05-07 |
| D3Net: Densely connected multidilated DenseNet for music source separation | ✓ Link | 6.01 | 7.24 | 7.01 | 5.25 | 4.53 | D3Net | 2020-10-05 |
| Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models | ✓ Link | 5.91 | 6.86 | 6.71 | 5.51 | 4.02 | Spleeter (MWF) | 2019-11-04 |
| LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation | ✓ Link | 5.88 | 7.33 | 5.68 | 5.63 | 4.87 | LaSAFT+GPoCM | 2020-10-22 |
| All for One and One for All: Improving Music Separation by Bridging Networks | ✓ Link | 5.79 | 6.61 | 6.47 | 5.43 | 4.64 | X-UMX | 2020-10-08 |
| Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation | ✓ Link | 5.73 | 6.81 | 6.08 | 5.66 | 4.37 | Conv-TasNet | 2018-09-20 |
| Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation | ✓ Link | 5.65 | 6.61 | 6.63 | 5.25 | 4.09 | Sams-Net | 2019-09-12 |
| Meta-learning Extractors for Music Source Separation | ✓ Link | 5.52 | 6.40 | 5.91 | 5.58 | 4.19 | Meta-TasNet | 2020-02-17 |
| Open-Unmix - A Reference Implementation for Music Source Separation | ✓ Link | 5.33 | 6.32 | 5.73 | 5.23 | 4.02 | UMX | 2019-09-08 |
| End-to-end music source separation: is it possible in the waveform domain? | ✓ Link | 3.5 | 3.46 | 4.60 | 2.49 | 0.54 | Wavenet | 2018-10-29 |
| Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation | ✓ Link | 3.23 | 3.25 | 4.22 | 3.21 | 2.25 | STL2 | 2018-06-08 |