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

arXiv: https://arxiv.org/abs/2112.04685 · HTML: https://mlsanity.com/paper/2112.04685/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 9 Dec 2021.

## Builds on (most cited first, 9 of 9)

- [Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed](https://mlsanity.com/paper/1909.01174/) (2019)
- [VoiceFixer: Toward General Speech Restoration with Neural Vocoder](https://mlsanity.com/paper/2109.13731/) (2021)
- [Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation](https://mlsanity.com/paper/2109.05418/) (2021)
- [D3Net: Densely connected multidilated DenseNet for music source separation](https://mlsanity.com/paper/2010.01733/) (2020)
- [All for One and One for All: Improving Music Separation by Bridging Networks](https://mlsanity.com/paper/2010.04228/) (2020)
- [MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation](https://mlsanity.com/paper/1805.02410/) (2018)
- [Channel-wise Subband Input for Better Voice and Accompaniment Separation on High Resolution Music](https://mlsanity.com/paper/2008.05216/) (2020)
- [Multi-channel U-Net for Music Source Separation](https://mlsanity.com/paper/2003.10414/) (2020)
- [Voice and accompaniment separation in music using self-attention convolutional neural network](https://mlsanity.com/paper/2003.08954/) (2020)

## Built on by (most cited first, 9 of 9)

- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [Separate What You Describe: Language-Queried Audio Source Separation](https://mlsanity.com/paper/2203.15147/) (2022)
- [Neural Vocoder is All You Need for Speech Super-resolution](https://mlsanity.com/paper/2203.14941/) (2022)
- [Music Separation Enhancement with Generative Modeling](https://mlsanity.com/paper/2208.12387/) (2022)
- [Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3](https://mlsanity.com/paper/2306.09382/) (2023)
- [MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement](https://mlsanity.com/paper/2310.04369/) (2023)
- [FlowSep 2: Self-Supervised Flow Matching for Language-Queried Audio Source Separation](https://mlsanity.com/paper/2608.22111/) (2026)
- [MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation](https://mlsanity.com/paper/2501.03689/) (2025)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)

## Abstract (arXiv)

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