# End-to-End Sound Source Separation Conditioned On Instrument Labels

arXiv: https://arxiv.org/abs/1811.01850 · HTML: https://mlsanity.com/paper/1811.01850/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2018.

## Built on by (most cited first, 5 of 5)

- [Visual Scene Graphs for Audio Source Separation](https://mlsanity.com/paper/2109.11955/) (2021)
- [A cappella: Audio-visual Singing Voice Separation](https://mlsanity.com/paper/2104.09946/) (2021)
- [Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation](https://mlsanity.com/paper/2210.16472/) (2022)
- [Environmental Sound Extraction Using Onomatopoeic Words](https://mlsanity.com/paper/2112.00209/) (2021)
- [User-guided Generative Source Separation](https://mlsanity.com/paper/2507.01339/) (2025)

## Abstract (arXiv)

Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? We present an extension of the Wave-U-Net model which allows end-to-end monaural source separation with a non-fixed number of sources. Furthermore, we propose multiplicative conditioning with instrument labels at the bottleneck of the Wave-U-Net and show its effect on the separation results. This approach leads to other types of conditioning such as audio-visual source separation and score-informed source separation.