# SCNet: Sparse Compression Network for Music Source Separation

arXiv: https://arxiv.org/abs/2401.13276 · HTML: https://mlsanity.com/paper/2401.13276/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2024.

## Built on by (most cited first, 10 of 10)

- [A Two-Stage Band-Split Mamba-2 Network For Music Separation](https://mlsanity.com/paper/2409.06245/) (2024)
- [User-guided Generative Source Separation](https://mlsanity.com/paper/2507.01339/) (2025)
- [An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separation](https://mlsanity.com/paper/2410.20773/) (2024)
- [The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval](https://mlsanity.com/paper/2511.21247/) (2025)
- [Source Separation of Small Classical Ensembles: Challenges and Opportunities](https://mlsanity.com/paper/2505.17823/) (2025)
- [Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions](https://mlsanity.com/paper/2508.14556/) (2025)
- [A Conditioned UNet for Music Source Separation](https://mlsanity.com/paper/2512.15532/) (2025)
- [Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation](https://mlsanity.com/paper/2604.01120/) (2026)
- [Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models](https://mlsanity.com/paper/2607.23395/) (2026)
- [Iterative Audio Separation with Mixture Consistency via MIMO Model Extension](https://mlsanity.com/paper/2609.07226/) (2026)

## Abstract (arXiv)

Deep learning-based methods have made significant achievements in music source separation. However, obtaining good results while maintaining a low model complexity remains challenging in super wide-band music source separation. Previous works either overlook the differences in subbands or inadequately address the problem of information loss when generating subband features. In this paper, we propose SCNet, a novel frequency-domain network to explicitly split the spectrogram of the mixture into several subbands and introduce a sparsity-based encoder to model different frequency bands. We use a higher compression ratio on subbands with less information to improve the information density and focus on modeling subbands with more information. In this way, the separation performance can be significantly improved using lower computational consumption. Experiment results show that the proposed model achieves a signal to distortion ratio (SDR) of 9.0 dB on the MUSDB18-HQ dataset without using extra data, which outperforms state-of-the-art methods. Specifically, SCNet's CPU inference time is only 48% of HT Demucs, one of the previous state-of-the-art models.