# Channel-wise Subband Input for Better Voice and Accompaniment Separation on High Resolution Music

arXiv: https://arxiv.org/abs/2008.05216 · HTML: https://mlsanity.com/paper/2008.05216/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2020.

## Built on by (most cited first, 13 of 13)

- [Separate What You Describe: Language-Queried Audio Source Separation](https://mlsanity.com/paper/2203.15147/) (2022)
- [FlowSep: Language-Queried Sound Separation with Rectified Flow Matching](https://mlsanity.com/paper/2409.07614/) (2024)
- [CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet](https://mlsanity.com/paper/2112.04685/) (2021)
- [Ultra Low Complexity Deep Learning Based Noise Suppression](https://mlsanity.com/paper/2312.08132/) (2023)
- [Learning Temporal Resolution in Spectrogram for Audio Classification](https://mlsanity.com/paper/2210.01719/) (2022)
- [Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3](https://mlsanity.com/paper/2306.09382/) (2023)
- [Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks](https://mlsanity.com/paper/2110.06525/) (2021)
- [Segment-level Metric Learning for Few-shot Bioacoustic Event Detection](https://mlsanity.com/paper/2207.07773/) (2022)
- [TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network](https://mlsanity.com/paper/2505.18533/) (2025)
- [FlowSep 2: Self-Supervised Flow Matching for Language-Queried Audio Source Separation](https://mlsanity.com/paper/2608.22111/) (2026)
- [Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method](https://mlsanity.com/paper/2105.04079/) (2021)
- [Sampling-Frequency-Independent Universal Sound Separation](https://mlsanity.com/paper/2309.12581/) (2023)
- [UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations](https://mlsanity.com/paper/2604.14606/) (2026)

## Abstract (arXiv)

This paper presents a new input format, channel-wise subband input (CWS), for convolutional neural networks (CNN) based music source separation (MSS) models in the frequency domain. We aim to address the major issues in CNN-based high-resolution MSS model: high computational cost and weight sharing between distinctly different bands. Specifically, in this paper, we decompose the input mixture spectra into several bands and concatenate them channel-wise as the model input. The proposed approach enables effective weight sharing in each subband and introduces more flexibility between channels. For comparison purposes, we perform voice and accompaniment separation (VAS) on models with different scales, architectures, and CWS settings. Experiments show that the CWS input is beneficial in many aspects. We evaluate our method on musdb18hq test set, focusing on SDR, SIR and SAR metrics. Among all our experiments, CWS enables models to obtain 6.9% performance gain on the average metrics. With even a smaller number of parameters, less training data, and shorter training time, our MDenseNet with 8-bands CWS input still surpasses the original MMDenseNet with a large margin. Moreover, CWS also reduces computational cost and training time to a large extent.