TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Methodology/2D Classification/MUSDB18-HQ

2D Classification on MUSDB18-HQ

Metric: SDR (vocals) (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕SDR (vocals)▼AugmentationsPaperDate↕Code
1BS-RoFormer (L=12, OA)12.72Yes---
2SCNet-large10.86NoSCNet: Sparse Compression Network for Music Sour...2024-01-24Code
3BS-RoFormer (L=6, OA)10.66No---
4Band-Split RNN (semi-sup.)10.47YesMusic Source Separation with Band-split RNN2022-09-30Code
5Dual-Path TFC-TDF UNet (DTTNet)10.21NoMusic Source Separation Based on a Lightweight D...2023-09-15Code
6Band-Split RNN10.01NoMusic Source Separation with Band-split RNN2022-09-30Code
7SCNet9.89NoSCNet: Sparse Compression Network for Music Sour...2024-01-24Code
8TFC-TDF-UNet (v3)9.59NoSound Demixing Challenge 2023 Music Demixing Tra...2023-06-15Code
9Sparse HT Demucs (fine tuned)9.37YesHybrid Transformers for Music Source Separation2022-11-15Code
10Hybrid Transformer Demucs (f.t.)9.2YesHybrid Transformers for Music Source Separation2022-11-15Code
11KUIELab-MDX-Net8.97NoKUIELab-MDX-Net: A Two-Stream Neural Network for...2021-11-24Code
12CWS-PResUNet8.92NoCWS-PResUNet: Music Source Separation with Chann...2021-12-09Code
13Hybrid Demucs8.13NoHybrid Spectrogram and Waveform Source Separation2021-11-05Code
14Unmix5.06NoTransfer Learning with Jukebox for Music Source ...2021-11-28Code