# All for One and One for All: Improving Music Separation by Bridging Networks

arXiv: https://arxiv.org/abs/2010.04228 · HTML: https://mlsanity.com/paper/2010.04228/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet](https://mlsanity.com/paper/2112.04685/) (2021)
- [JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus](https://mlsanity.com/paper/2211.16028/) (2022)
- [Weakly-supervised Audio Separation via Bi-modal Semantic Similarity](https://mlsanity.com/paper/2404.01740/) (2024)
- [Transfer Learning with Jukebox for Music Source Separation](https://mlsanity.com/paper/2111.14200/) (2021)
- [Toward Deep Drum Source Separation](https://mlsanity.com/paper/2312.09663/) (2023)
- [SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation](https://mlsanity.com/paper/2409.10995/) (2024)
- [Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet](https://mlsanity.com/paper/2402.17701/) (2024)
- [OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation](https://mlsanity.com/paper/2409.19270/) (2024)
- [Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music](https://mlsanity.com/paper/2503.07352/) (2025)
- [Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data](https://mlsanity.com/paper/2307.12576/) (2023)
- [The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss](https://mlsanity.com/paper/2409.05095/) (2024)
- [The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval](https://mlsanity.com/paper/2511.21247/) (2025)
- [LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation](https://mlsanity.com/paper/2111.12516/) (2021)
- [Activity-Guided Industrial Anomalous Sound Detection against Interferences](https://mlsanity.com/paper/2409.01885/) (2024)
- [Source Separation of Small Classical Ensembles: Challenges and Opportunities](https://mlsanity.com/paper/2505.17823/) (2025)
- [Source Separation for A Cappella Music](https://mlsanity.com/paper/2509.26580/) (2025)
- [A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separation](https://mlsanity.com/paper/2602.21476/) (2026)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)
- [SCISSOR: Score-Conditioned Instrument Source Separation for Orchestral Recordings](https://mlsanity.com/paper/2609.33265/) (2026)

## Abstract (arXiv)

This paper proposes several improvements for music separation with deep neural networks (DNNs), namely a multi-domain loss (MDL) and two combination schemes. First, by using MDL we take advantage of the frequency and time domain representation of audio signals. Next, we utilize the relationship among instruments by jointly considering them. We do this on the one hand by modifying the network architecture and introducing a CrossNet structure. On the other hand, we consider combinations of instrument estimates by using a new combination loss (CL). MDL and CL can easily be applied to many existing DNN-based separation methods as they are merely loss functions which are only used during training and which do not affect the inference step. Experimental results show that the performance of Open-Unmix (UMX), a well-known and state-of-the-art open source library for music separation, can be improved by utilizing our above schemes. Our modifications of UMX are open-sourced together with this paper.