Papers › Meta-learning Extractors for Music Source Separation

Meta-learning Extractors for Music Source Separation

17 Feb 2020arXiv:2002.07016archive 2025-07-28

David Samuel, Aditya Ganeshan, Jason Naradowsky

We propose a hierarchical meta-learning-inspired model for music source separation (Meta-TasNet) in which a generator model is used to predict the weights of individual extractor models. This enables efficient parameter-sharing, while still allowing for instrument-specific parameterization. Meta-TasNet is shown to be more effective than the models trained independently or in a multi-task setting, and achieve performance comparable with state-of-the-art methods. In comparison to the latter, our extractors contain fewer parameters and have faster run-time performance. We discuss important architectural considerations, and explore the costs and benefits of this approach.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

pfnet-research/meta-tasnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation (arXiv:1809.07454; that paper's own run record: 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); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Meta-LearningMusic Source Separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Music Source Separation MUSDB18 Meta-TasNet SDR (avg) 5.52 #24 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Meta-TasNet SDR (bass) 5.58 #24 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Meta-TasNet SDR (drums) 5.91 #24 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Meta-TasNet SDR (other) 4.19 #24 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Meta-TasNet SDR (vocals) 6.40 #24 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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