Papers › Hybrid Spectrogram and Waveform Source Separation

Hybrid Spectrogram and Waveform Source Separation

5 Nov 2021arXiv:2111.03600archive 2025-07-28

Alexandre Défossez

Source separation models either work on the spectrogram or waveform domain. In this work, we show how to perform end-to-end hybrid source separation, letting the model decide which domain is best suited for each source, and even combining both. The proposed hybrid version of the Demucs architecture won the Music Demixing Challenge 2021 organized by Sony. This architecture also comes with additional improvements, such as compressed residual branches, local attention or singular value regularization. Overall, a 1.4 dB improvement of the Signal-To-Distortion (SDR) was observed across all sources as measured on the MusDB HQ dataset, an improvement confirmed by human subjective evaluation, with an overall quality rated at 2.83 out of 5 (2.36 for the non hybrid Demucs), and absence of contamination at 3.04 (against 2.37 for the non hybrid Demucs and 2.44 for the second ranking model submitted at the competition).

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

facebookresearch/demucs officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Abusive music and song transformation using GenAI and LLMs (arXiv:2601.15348; that paper's own run record: 7 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; 3 where Syntology's instrument failed) · 1 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

Music Source Separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Music Source Separation MUSDB18 Hybrid Demucs SDR (avg) 7.72 #6 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Hybrid Demucs SDR (bass) 8.67 #6 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Hybrid Demucs SDR (drums) 8.58 #6 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Hybrid Demucs SDR (other) 5.59 #6 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Hybrid Demucs SDR (vocals) 8.04 #6 of 27 Archive leaderboard report
Music Source Separation MUSDB18-HQ Hybrid Demucs SDR (avg) 7.68 #11 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ Hybrid Demucs SDR (bass) 8.76 #11 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ Hybrid Demucs SDR (drums) 8.24 #11 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ Hybrid Demucs SDR (others) 5.59 #11 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ Hybrid Demucs SDR (vocals) 8.13 #11 of 14 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