Datasets › MUSDB18

MUSDB18

Introduced in The MUSDB18 corpus for music separation archive 2025-07-28

The MUSDB18 is a dataset of 150 full lengths music tracks (~10h duration) of different genres along with their isolated drums, bass, vocals and others stems.

The dataset is split into training and test sets with 100 and 50 songs, respectively. All signals are stereophonic and encoded at 44.1kHz.

Source: https://sigsep.github.io/datasets/musdb.html#musdb18-compressed-stems Image Source: https://sigsep.github.io/datasets/musdb.html#musdb18-compressed-stems

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Music Source Separation MUSDB18 Sparse HT Demucs (fine tuned) SDR (avg) 9.20 Hybrid Transformers for Music Source Separation facebookresearch/demucs +1 27 Compare
Cadenza 1 - Task 1 - Headphone MUSDB18 Baseline Demucs HAAQI 0.2592 The First Cadenza Signal Processing Challenge: Improving... claritychallenge/clarity 2 Compare

Papers archive 2025-07-28

papers with a benchmark row: 22 · with a code link: 20 · where Syntology ran a sample: 8 (7 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (8 of 22 with a benchmark row: 7 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 22 of 22 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 106. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
The First Cadenza Signal Processing Challenge: Improving Music for Those With a Hearing Loss 1 2 9 Oct 2023 not harvested
Contrastive Learning based Deep Latent Masking for Music Source Separation 0 1 20 Aug 2023 not harvested
Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3 1 1 15 Jun 2023 not harvested
Hybrid Transformers for Music Source Separation 2 2 15 Nov 2022 community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (10 pointer-only for licence)
An Efficient Short-Time Discrete Cosine Transform and Attentive MultiResUNet Framework for Music Source Separation 1 1 14 Nov 2022 not harvested
Music Source Separation with Band-split RNN 3 2 30 Sep 2022 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified
Hierarchic Temporal Convolutional Network With Cross-Domain Encoder for Music Source Separation 0 1 30 Jun 2022 not harvested
CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet 1 1 9 Dec 2021 not harvested
KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing 1 1 24 Nov 2021 not harvested
Hybrid Spectrogram and Waveform Source Separation 1 1 5 Nov 2021 not harvested
LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation 1 1 22 Oct 2020 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified
All for One and One for All: Improving Music Separation by Bridging Networks 5 1 8 Oct 2020 official (archive's flag): 7 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
D3Net: Densely connected multidilated DenseNet for music source separation 1 2 5 Oct 2020 not harvested
Meta-learning Extractors for Music Source Separation 1 1 17 Feb 2020 not harvested
Music Source Separation in the Waveform Domain 1 2 27 Nov 2019 not harvested
Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models 3 1 4 Nov 2019 not harvested
Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation 1 1 12 Sep 2019 not harvested
Open-Unmix - A Reference Implementation for Music Source Separation 1 2 8 Sep 2019 not harvested
End-to-end music source separation: is it possible in the waveform domain? 2 1 29 Oct 2018 community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation 17 2 20 Sep 2018 community repositories only · 28 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 3 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified (16 pointer-only for licence)
Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation 10 1 8 Jun 2018 official (archive's flag): 3 ran · 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified (1 pointer-only for licence)
MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation 1 1 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified

Dataset loaders archive 2025-07-28

3 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Various (see link)

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • MUSDB18

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections