Browse State-of-the-Art › Audio Source Separation
Audio Source Separation
54 papers with code · 2 benchmarks · 15 datasets archive 2025-07-28
Audio Source Separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals).
Source: Model selection for deep audio source separation via clustering analysis
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| AudioSet (2 rows) | ST-SED-SEP | Zero-shot Audio Source Separation through Query-based Learning... | code | Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified | Compare |
| MUSIC (multi-source) (1 row) | Co-Separation | Co-Separating Sounds of Visual Objects | 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
15 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
3 subtasks in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 112 · with a code link: 54 · where Syntology ran a sample: 15 (15 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (15 of 112 tagged: 15 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 112, 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.
-
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.
-
29 Jun 2017 5 repositories listedThis paper deals with the problem of audio source separation.
-
14 Jul 2020 4 repositories listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 1 pointer-only (licence)In this paper, we present an efficient neural network for end-to-end general purpose audio source separation.
-
19 Oct 2021 3 repositories listed Syntology 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) · 0 unverified (of 4 harvested samples)The cocktail party problem aims at isolating any source of interest within a complex acoustic scene, and has long inspired audio source separation research.
-
3 Mar 2021 3 repositories listedRecent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem.
-
16 Apr 2019 3 repositories listedLearning how objects sound from video is challenging, since they often heavily overlap in a single audio channel.
-
27 Nov 2018 3 repositories listedWe study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment.
-
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.
-
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…
-
30 Jan 2021 2 repositories listedIn blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix.
-
2 Jul 2019 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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)The input vector is embedded to obtain the parameters that control Feature-wise Linear Modulation (FiLM) layers.
-
5 Apr 2018 2 repositories listedOur work is the first to learn audio source separation from large-scale "in the wild" videos containing multiple audio sources per video.
-
15 Jul 2025 1 repository listedTraditional Blind Source Separation Evaluation (BSS-Eval) metrics were originally designed to evaluate linear audio source separation models based on methods such as time-frequency masking.
-
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…
-
2 Nov 2024 1 repository listedSound Event Detection (SED) is challenging in noisy environments where overlapping sounds obscure target events.
-
20 Sep 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 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; 7 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)To address this issue, we propose the text-queried SED (TQ-SED) framework.
-
19 Aug 2024 1 repository listedWe demonstrate that our framework, used with diffusion models, naturally addresses the task of unsupervised audio source separation, showing that our model is able to perform high-quality separation.
-
7 Aug 2024 1 repository listedIn this work, we demonstrate a very straightforward extension of the dedicated-decoder Bandit and query-based single-decoder Banquet models to a four-stem problem, treating non-musical dialogue, instrumental music…
-
9 Jul 2024 1 repository listedCinematic audio source separation (CASS), as a problem of extracting the dialogue, music, and effects stems from their mixture, is a relatively new subtask of audio source separation.
-
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 May 2024 1 repository listedThe combination of frequency-axis normalization with Min/Max scaling and the Mean Absolute Error (MAE) loss function achieved the highest Source-to-Distortion Ratio (SDR) of 7.
-
5 Sep 2023 1 repository listedCinematic audio source separation is a relatively new subtask of audio source separation, with the aim of extracting the dialogue, music, and effects stems from their mixture.
-
9 Aug 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 3 pointer-only (licence)In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries.
-
29 Oct 2022 1 repository listed Syntology 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) · 1 unverified (of 2 harvested samples)In this paper, we propose to use this connection between audio and visual dynamics for solving two challenging tasks simultaneously, namely: (i) separating audio sources from a mixture using visual cues, and (ii)…
-
21 Jul 2022 1 repository listedA network with relevant deep priors is likely to generate a cleaner version of the signal before converging on the corrupted signal.
-
28 Mar 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language query of the target source (e. g., "a man…
-
15 Dec 2021 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 3 pointer-only (licence)Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training.
-
11 Dec 2021 1 repository listedOn-device directional hearing requires audio source separation from a given direction while achieving stringent human-imperceptible latency requirements.
-
28 Nov 2021 1 repository listedIn this work, we demonstrate how a publicly available, pre-trained Jukebox model can be adapted for the problem of audio source separation from a single mixed audio channel.
-
25 Oct 2021 1 repository listedWe showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining.
-
11 Oct 2021 1 repository listed
-
24 Sep 2021 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) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
14 Jul 2021 1 repository listed
-
19 Jun 2021 1 repository listed
-
17 May 2021 1 repository listed Syntology official (archive's flag): 8 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) · 1 unverified (of 9 harvested samples)
-
10 May 2021 1 repository listed
-
20 Apr 2021 1 repository listed
-
3 Feb 2021 1 repository listed
-
21 Nov 2020 1 repository listed
-
25 Oct 2020 1 repository listed
-
12 Oct 2020 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
25 Jul 2020 1 repository listed
-
12 Jul 2020 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) · 0 unverified (of 4 harvested samples)
-
28 May 2020 1 repository listed
-
28 Jan 2020 1 repository listed
-
29 Nov 2019 1 repository listed
-
25 Sep 2019 1 repository listed
-
12 Sep 2019 1 repository listed
-
17 Jun 2019 1 repository listed
-
29 May 2019 1 repository listed
-
31 Oct 2018 1 repository listed
-
30 Oct 2018 1 repository listed
-
10 Apr 2018 1 repository listed
-
23 Mar 2018 1 repository listed
-
DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization3 Jun 2025 0 repositories listed
-
ZeroSep: Separate Anything in Audio with Zero Training29 May 2025 0 repositories listed
-
Text-Queried Audio Source Separation via Hierarchical Modeling27 May 2025 0 repositories listed
-
Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond7 May 2025 0 repositories listed
-
Automatic Identification of Samples in Hip-Hop Music via Multi-Loss Training and an Artificial Dataset10 Feb 2025 0 repositories listed
-
Study of the Performance of CEEMDAN in Underdetermined Speech Separation18 Nov 2024 0 repositories listed
-
Task-Aware Unified Source Separation31 Oct 2024 0 repositories listed
-
Semantic Grouping Network for Audio Source Separation4 Jul 2024 0 repositories listed
-
Performance Improvement of Language-Queried Audio Source Separation Based on Caption Augmentation From Large Language Models for DCASE Challenge 2024 Task 917 Jun 2024 0 repositories listed
-
Low algorithmic delay implementation of convolutional beamformer for online joint source separation and dereverberation14 Jun 2024 0 repositories listed
-
Gull: A Generative Multifunctional Audio Codec7 Apr 2024 0 repositories listed
-
Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation7 Dec 2023 0 repositories listed
-
GASS: Generalizing Audio Source Separation with Large-scale Data29 Sep 2023 0 repositories listed
-
Language-Guided Audio-Visual Source Separation via Trimodal Consistency28 Mar 2023 0 repositories listed
-
25 Jan 2023 0 repositories listed
-
Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks14 Dec 2022 0 repositories listed
-
Hyperbolic Audio Source Separation9 Dec 2022 0 repositories listed
-
Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation28 Nov 2022 0 repositories listed
-
30 Jun 2022 0 repositories listed
-
Sampling Frequency Independent Dialogue Separation5 Jun 2022 0 repositories listed
-
24 May 2022 0 repositories listed
-
On loss functions and evaluation metrics for music source separation16 Feb 2022 0 repositories listed
-
Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds1 Feb 2022 0 repositories listed
-
Fish sounds: towards the evaluation of marine acoustic biodiversity through data-driven audio source separation13 Jan 2022 0 repositories listed
-
Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning5 Jan 2022 0 repositories listed
-
Zero-shot Audio Source Separation through Query-based Learningfrom Weakly-labeled Data15 Dec 2021 0 repositories listed
-
Reduction of Subjective Listening Effort for TV Broadcast Signals with Recurrent Neural Networks2 Nov 2021 0 repositories listed
-
Move2Hear: Active Audio-Visual Source Separation15 May 2021 0 repositories listed
-
MULTIMODAL ANALYSIS: Informed content estimation and audio source separation27 Apr 2021 0 repositories listed
-
Weakly-supervised Audio-visual Sound Source Detection and Separation25 Mar 2021 0 repositories listed
-
Problems using deep generative models for probabilistic audio source separation3 Nov 2020 0 repositories listed
-
A Study of Transfer Learning in Music Source Separation23 Oct 2020 0 repositories listed
-
Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm22 Oct 2020 0 repositories listed
-
Fast accuracy estimation of deep learning based multi-class musical source separation19 Oct 2020 0 repositories listed
-
Adversarial attacks on audio source separation7 Oct 2020 0 repositories listed
-
Structure and Automatic Segmentation of Dhrupad Vocal Bandish Audio3 Aug 2020 0 repositories listed
-
Cooperative Audio Source Separation and Enhancement Using Distributed Microphone Arrays and Wearable Devices10 Dec 2019 0 repositories listed
-
WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation21 Nov 2019 0 repositories listed
-
Improving Universal Sound Separation Using Sound Classification18 Nov 2019 0 repositories listed
-
Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision6 Nov 2019 0 repositories listed
-
Model selection for deep audio source separation via clustering analysis23 Oct 2019 0 repositories listed
-
Retrieving Signals with Deep Complex Extractors14 Sep 2019 0 repositories listed
-
Interleaved Multitask Learning for Audio Source Separation with Independent Databases14 Aug 2019 0 repositories listed
-
Blind Audio Source Separation with Minimum-Volume Beta-Divergence NMF4 Jul 2019 0 repositories listed
-
Generalized Separable Nonnegative Matrix Factorization30 May 2019 0 repositories listed
-
Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets8 Apr 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