Music Source Separation

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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

30 shown of 58 papers with code (107 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
  20 Sep 2018 17 repositories listed Syntology ran 7 of 36 samples · 29 unverified · 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…
• Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation
  8 Jun 2018 10 repositories listed Syntology ran 1 of 19 samples · 18 unverified · 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.
• All for One and One for All: Improving Music Separation by Bridging Networks
  8 Oct 2020 5 repositories listed Syntology ran 1 of 10 samples · 9 unverified
  This paper proposes several improvements for music separation with deep neural networks (DNNs), namely a multi-domain loss (MDL) and two combination schemes.
• Multi-scale Multi-band DenseNets for Audio Source Separation
  29 Jun 2017 5 repositories listed
  This paper deals with the problem of audio source separation.
• SCNet: Sparse Compression Network for Music Source Separation
  24 Jan 2024 3 repositories listed
  We use a higher compression ratio on subbands with less information to improve the information density and focus on modeling subbands with more information.
• Music Source Separation with Band-split RNN
  30 Sep 2022 3 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  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.
• Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models
  4 Nov 2019 3 repositories listed
  We present and release a new tool for music source separation with pre-trained models called Spleeter.
• Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction
  31 Oct 2017 3 repositories listed Syntology ran 0 of 13 samples · 13 unverified
  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.
• Learned Compression for Compressed Learning
  12 Dec 2024 2 repositories listed
  Linear transform coding and end-to-end learned compression systems reduce bitrate, but do not uniformly reduce dimensionality; thus, they do not meaningfully increase efficiency.
• SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
  17 Sep 2024 2 repositories listed
  Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks.
• Pre-training Music Classification Models via Music Source Separation
  24 Oct 2023 2 repositories listed
  In 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.
• Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)
  15 Sep 2023 2 repositories listed
  Music source separation (MSS) aims to extract 'vocals', 'drums', 'bass' and 'other' tracks from a piece of mixed music.
• The Sound Demixing Challenge 2023 x2013 Music Demixing Track
  14 Aug 2023 2 repositories listed
  We 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.
• Hybrid Transformers for Music Source Separation
  15 Nov 2022 2 repositories listed Syntology ran 0 of 10 samples · 10 unverified · 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.
• Unsupervised Music Source Separation Using Differentiable Parametric Source Models
  24 Jan 2022 2 repositories listed
  Integrating 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…
• A cappella: Audio-visual Singing Voice Separation
  20 Apr 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The task of isolating a target singing voice in music videos has useful applications.
• Multi-channel U-Net for Music Source Separation
  23 Mar 2020 2 repositories listed
  However, 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.
• End-to-end music source separation: is it possible in the waveform domain?
  29 Oct 2018 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 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.
• Primal-Dual Algorithms for Non-negative Matrix Factorization with the Kullback-Leibler Divergence
  4 Dec 2014 2 repositories listed
  Non-negative matrix factorization (NMF) approximates a given matrix as a product of two non-negative matrices.
• Music Source Restoration
  27 May 2025 1 repository listed
  We introduce Music Source Restoration (MSR), a novel task addressing the gap between idealized source separation and real-world music production.
• Training-Free Multi-Step Audio Source Separation
  26 May 2025 1 repository listed
  Our 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…
• Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music
  10 Mar 2025 1 repository listed
  Music source separation is the task of separating a mixture of instruments into constituent tracks.
• A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems
  26 Jun 2024 1 repository listed Syntology ran 4 of 4 samples · 0 unverified
  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.
• A fully differentiable model for unsupervised singing voice separation
  30 Jan 2024 1 repository listed
  A novel model was recently proposed by Schulze-Forster et al.
• Machine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image Models
  15 Jan 2024 1 repository listed
  Our 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…
• Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3
  15 Jun 2023 1 repository listed
  In this report, we present our award-winning solutions for the Music Demixing Track of Sound Demixing Challenge 2023.
• Quantifying Spatial Audio Quality Impairment
  13 Jun 2023 1 repository listed
  Spatial audio quality is a highly multifaceted concept, with many interactions between environmental, geometrical, anatomical, psychological, and contextual considerations.
• The Whole Is Greater than the Sum of Its Parts: Improving Music Source Separation by Bridging Network
  13 May 2023 1 repository listed
  We modify the target network, i.
• MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation
  14 Nov 2022 1 repository listed
  Second, 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.
• An Efficient Short-Time Discrete Cosine Transform and Attentive MultiResUNet Framework for Music Source Separation
  14 Nov 2022 1 repository listed
  The 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…

Syntology lines on 9 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. Read from the graph 2026-09-24.