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

Code

facebookresearch/demucs officialmentioned in papermentioned on GitHubpytorch 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.

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