Browse State-of-the-Art › Music Source Separation
Music Source Separation
58 papers with code · 3 benchmarks · 9 datasets archive 2025-07-28
Music source separation is the task of decomposing music into its constitutive components, e. g., yielding separated stems for the vocals, bass, and drums.
( Image credit: SigSep )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): MUSDB18-HQ (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| MUSDB18 (27 rows) | Sparse HT Demucs (fine tuned) | Hybrid Transformers for Music Source Separation | code | Syntology 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 | Compare |
| MUSDB18-HQ (14 rows) | BS-RoFormer (L=12, OA) | — | — | — | Compare |
| Slakh2100 (2 rows) | LQ-VAE + Scalable Transformer | Unsupervised Source Separation via Bayesian Inference in the Latent Domain | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each 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”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is 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. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
9 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 107 · with a code link: 58 · where Syntology ran a sample: 15 (13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (15 of 107 tagged: 13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 107, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology 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”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
20 Sep 2018 17 repositories listed Syntology 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 (of 36 harvested samples) · 16 pointer-only (licence)The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude…
-
8 Jun 2018 10 repositories listed Syntology 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 (of 19 harvested samples) · 1 pointer-only (licence)Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end.
-
8 Oct 2020 5 repositories listed Syntology 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 (of 10 harvested samples)This paper proposes several improvements for music separation with deep neural networks (DNNs), namely a multi-domain loss (MDL) and two combination schemes.
-
29 Jun 2017 5 repositories listedThis paper deals with the problem of audio source separation.
-
24 Jan 2024 3 repositories listedWe use a higher compression ratio on subbands with less information to improve the information density and focus on modeling subbands with more information.
-
30 Sep 2022 3 repositories listed Syntology 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 (of 10 harvested samples)The performance of music source separation (MSS) models has been greatly improved in recent years thanks to the development of novel neural network architectures and training pipelines.
-
4 Nov 2019 3 repositories listedWe present and release a new tool for music source separation with pre-trained models called Spleeter.
-
31 Oct 2017 3 repositories listed Syntology official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified (of 13 harvested samples)Based on this idea, we drive the separator towards outputs deemed as realistic by discriminator networks that are trained to tell apart real from separator samples.
-
12 Dec 2024 2 repositories listedLinear transform coding and end-to-end learned compression systems reduce bitrate, but do not uniformly reduce dimensionality; thus, they do not meaningfully increase efficiency.
-
17 Sep 2024 2 repositories listedRecent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks.
-
24 Oct 2023 2 repositories listedIn this paper, we study whether music source separation can be used as a pre-training strategy for music representation learning, targeted at music classification tasks.
-
15 Sep 2023 2 repositories listedMusic source separation (MSS) aims to extract 'vocals', 'drums', 'bass' and 'other' tracks from a piece of mixed music.
-
14 Aug 2023 2 repositories listedWe propose a formalization of the errors that can occur in the design of a training dataset for MSS systems and introduce two new datasets that simulate such errors: SDXDB23_LabelNoise and SDXDB23_Bleeding.
-
15 Nov 2022 2 repositories listed Syntology 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 (of 10 harvested samples) · 10 pointer-only (licence)While it performs poorly when trained only on MUSDB, we show that it outperforms Hybrid Demucs (trained on the same data) by 0.
-
24 Jan 2022 2 repositories listedIntegrating domain knowledge in the form of source models into a data-driven method leads to high data efficiency: the proposed approach achieves good separation quality even when trained on less than three minutes of…
-
20 Apr 2021 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)The task of isolating a target singing voice in music videos has useful applications.
-
23 Mar 2020 2 repositories listedHowever, Conditioned U-Net (C-U-Net) uses a control mechanism to train a single model for multi-source separation and attempts to achieve a performance comparable to that of the dedicated models.
-
29 Oct 2018 2 repositories listed Syntology 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 (of 1 harvested sample) · 1 pointer-only (licence)Most of the currently successful source separation techniques use the magnitude spectrogram as input, and are therefore by default omitting part of the signal: the phase.
-
4 Dec 2014 2 repositories listedNon-negative matrix factorization (NMF) approximates a given matrix as a product of two non-negative matrices.
-
27 May 2025 1 repository listedWe introduce Music Source Restoration (MSR), a novel task addressing the gap between idealized source separation and real-world music production.
-
26 May 2025 1 repository listedOur empirical results demonstrate that our multi-step separation approach consistently outperforms one-step inference across both speech enhancement and music source separation tasks, and can achieve scaling performance…
-
10 Mar 2025 1 repository listedMusic source separation is the task of separating a mixture of instruments into constituent tracks.
-
26 Jun 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)Of the very few current systems that support source separation beyond this setup, most continue to rely on an inflexible decoder setup that can only support a fixed pre-defined set of stems.
-
30 Jan 2024 1 repository listedA novel model was recently proposed by Schulze-Forster et al. in [1] for unsupervised music source separation.
-
15 Jan 2024 1 repository listedOur results indicate three key findings: (1) using generative compression, it is feasible to leverage highly compressed data while incurring a negligible impact on machine perceptual quality; (2) machine perceptual…
-
15 Jun 2023 1 repository listedIn this report, we present our award-winning solutions for the Music Demixing Track of Sound Demixing Challenge 2023.
-
13 Jun 2023 1 repository listedSpatial audio quality is a highly multifaceted concept, with many interactions between environmental, geometrical, anatomical, psychological, and contextual considerations.
-
13 May 2023 1 repository listedWe modify the target network, i. e., the network architecture of the original DNN-based MSS, by adding bridging paths for each output instrument to share their information.
-
14 Nov 2022 1 repository listedThe proposed network is used for the first time in source separation and is more computationally efficient than state-of-the-art separation networks and features favourable performance compared to the state-of-the-art…
-
14 Nov 2022 1 repository listedSecond, to overcome the absence of existing multi-singing datasets for a training purpose, we present a strategy for construction of multiple singing mixtures using various single-singing datasets.
-
4 Nov 2022 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 14 harvested samples)
-
19 Apr 2022 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)
-
12 Apr 2022 1 repository listed
-
5 Apr 2022 1 repository listed
-
9 Dec 2021 1 repository listed
-
7 Dec 2021 1 repository listed
-
28 Nov 2021 1 repository listed
-
24 Nov 2021 1 repository listed
-
5 Nov 2021 1 repository listed
-
11 Oct 2021 1 repository listed
-
31 Aug 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 7 harvested samples)
-
7 Aug 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples)
-
14 Jul 2021 1 repository listed
-
10 May 2021 1 repository listed
-
3 Feb 2021 1 repository listed
-
21 Nov 2020 1 repository listed
-
22 Oct 2020 1 repository listed Syntology 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 (of 3 harvested samples)
-
5 Oct 2020 1 repository listed
-
6 Aug 2020 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
3 Mar 2020 1 repository listed
-
17 Feb 2020 1 repository listed
-
28 Jan 2020 1 repository listed
-
27 Nov 2019 1 repository listed
-
12 Sep 2019 1 repository listed
-
8 Sep 2019 1 repository listed
-
3 Sep 2019 1 repository listed
-
14 Dec 2018 1 repository listed
-
7 Jul 2018 1 repository listed
-
Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation12 May 2025 0 repositories listed
-
Solving Copyright Infringement on Short Video Platforms: Novel Datasets and an Audio Restoration Deep Learning Pipeline30 Apr 2025 0 repositories listed
-
Separate This, and All of these Things Around It: Music Source Separation via Hyperellipsoidal Queries27 Jan 2025 0 repositories listed
-
Sanidha: A Studio Quality Multi-Modal Dataset for Carnatic Music12 Jan 2025 0 repositories listed
-
MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation7 Jan 2025 0 repositories listed
-
Music Foundation Model as Generic Booster for Music Downstream Tasks2 Nov 2024 0 repositories listed
-
Task-Aware Unified Source Separation31 Oct 2024 0 repositories listed
-
An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separation28 Oct 2024 0 repositories listed
-
Improving Real-Time Music Accompaniment Separation with MMDenseNet30 Jun 2024 0 repositories listed
-
Why does music source separation benefit from cacophony?28 Feb 2024 0 repositories listed
-
Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet27 Feb 2024 0 repositories listed
-
Resource-constrained stereo singing voice cancellation22 Jan 2024 0 repositories listed
-
Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference6 Dec 2023 0 repositories listed
-
Pre-trained Spatial Priors on Multichannel NMF for Music Source Separation9 Oct 2023 0 repositories listed
-
MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement6 Oct 2023 0 repositories listed
-
20 Aug 2023 0 repositories listed
-
Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data24 Jul 2023 0 repositories listed
-
Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT4 Apr 2023 0 repositories listed
-
Hybrid Y-Net Architecture for Singing Voice Separation5 Mar 2023 0 repositories listed
-
Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training1 Feb 2023 0 repositories listed
-
Multi-scale temporal-frequency attention for music source separation2 Sep 2022 0 repositories listed
-
Music Separation Enhancement with Generative Modeling26 Aug 2022 0 repositories listed
-
30 Jun 2022 0 repositories listed
-
19 Jun 2022 0 repositories listed
-
Feature-informed Latent Space Regularization for Music Source Separation17 Mar 2022 0 repositories listed
-
On loss functions and evaluation metrics for music source separation16 Feb 2022 0 repositories listed
-
SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation15 Feb 2022 0 repositories listed
-
Distortion Audio Effects: Learning How to Recover the Clean Signal3 Feb 2022 0 repositories listed
-
Upsampling layers for music source separation23 Nov 2021 0 repositories listed
-
A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation16 Jun 2021 0 repositories listed
-
HTMD-Net: A Hybrid Masking-Denoising Approach to Time-Domain Monaural Singing Voice Separation7 Mar 2021 0 repositories listed
-
Adversarial Unsupervised Domain Adaptation for Harmonic-Percussive Source Separation3 Jan 2021 0 repositories listed
-
Source Separation and Depthwise Separable Convolutions for Computer Audition6 Dec 2020 0 repositories listed
-
A Study of Transfer Learning in Music Source Separation23 Oct 2020 0 repositories listed
-
Transcription Is All You Need: Learning to Separate Musical Mixtures with Score as Supervision22 Oct 2020 0 repositories listed
-
Fast accuracy estimation of deep learning based multi-class musical source separation19 Oct 2020 0 repositories listed
-
A frugal approach to music source separation2 Oct 2020 0 repositories listed
-
Multitask learning for instrument activation aware music source separation3 Aug 2020 0 repositories listed
-
Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation6 Jul 2020 0 repositories listed
-
Voice and accompaniment separation in music using self-attention convolutional neural network19 Mar 2020 0 repositories listed
-
Bootstrapping deep music separation from primitive auditory grouping principles23 Oct 2019 0 repositories listed
-
18 Sep 2019 0 repositories listed
Syntology lines on 15 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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