Papers › CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet

CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet

9 Dec 2021arXiv:2112.04685archive 2025-07-28

Haohe Liu, Qiuqiang Kong, Jiafeng Liu

Music source separation (MSS) shows active progress with deep learning models in recent years. Many MSS models perform separations on spectrograms by estimating bounded ratio masks and reusing the phases of the mixture. When using convolutional neural networks (CNN), weights are usually shared within a spectrogram during convolution regardless of the different patterns between frequency bands. In this study, we propose a new MSS model, channel-wise subband phase-aware ResUNet (CWS-PResUNet), to decompose signals into subbands and estimate an unbound complex ideal ratio mask (cIRM) for each source. CWS-PResUNet utilizes a channel-wise subband (CWS) feature to limit unnecessary global weights sharing on the spectrogram and reduce computational resource consumptions. The saved computational cost and memory can in turn allow for a larger architecture. On the MUSDB18HQ test set, we propose a 276-layer CWS-PResUNet and achieve state-of-the-art (SoTA) performance on vocals with an 8.92 signal-to-distortion ratio (SDR) score. By combining CWS-PResUNet and Demucs, our ByteMSS system ranks the 2nd on vocals score and 5th on average score in the 2021 ISMIR Music Demixing (MDX) Challenge limited training data track (leaderboard A). Our code and pre-trained models are publicly available at: https://github.com/haoheliu/2021-ISMIR-MSS-Challenge-CWS-PResUNet

PaperPDFCode

Code

haoheliu/2021-ismir-mss-challenge-cws-presunet 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 CWS-PResUNet SDR (avg) 6.77 #11 of 27 Archive leaderboard report
Music Source Separation MUSDB18 CWS-PResUNet SDR (bass) 5.93 #11 of 27 Archive leaderboard report
Music Source Separation MUSDB18 CWS-PResUNet SDR (drums) 6.38 #11 of 27 Archive leaderboard report
Music Source Separation MUSDB18 CWS-PResUNet SDR (other) 5.84 #11 of 27 Archive leaderboard report
Music Source Separation MUSDB18 CWS-PResUNet SDR (vocals) 8.92 #11 of 27 Archive leaderboard report
Music Source Separation MUSDB18-HQ CWS-PResUNet SDR (avg) 6.77 #13 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ CWS-PResUNet SDR (bass) 5.93 #13 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ CWS-PResUNet SDR (drums) 6.38 #13 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ CWS-PResUNet SDR (others) 5.84 #13 of 14 Archive leaderboard report
Music Source Separation MUSDB18-HQ CWS-PResUNet SDR (vocals) 8.92 #13 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.

Methods

Convolution

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