# Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations

arXiv: https://arxiv.org/abs/1907.01277 · HTML: https://mlsanity.com/paper/1907.01277/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

## Built on by (most cited first, 27 of 27)

- [CRASH: Raw Audio Score-based Generative Modeling for Controllable High-resolution Drum Sound Synthesis](https://mlsanity.com/paper/2106.07431/) (2021)
- [Visual Scene Graphs for Audio Source Separation](https://mlsanity.com/paper/2109.11955/) (2021)
- [A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis](https://mlsanity.com/paper/2108.03456/) (2021)
- [Heterogeneous Target Speech Separation](https://mlsanity.com/paper/2204.03594/) (2022)
- [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)
- [A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems](https://mlsanity.com/paper/2406.18747/) (2024)
- [Jointist: Joint Learning for Multi-instrument Transcription and Its Applications](https://mlsanity.com/paper/2206.10805/) (2022)
- [Music Foundation Model as Generic Booster for Music Downstream Tasks](https://mlsanity.com/paper/2411.01135/) (2024)
- [Optimal Condition Training for Target Source Separation](https://mlsanity.com/paper/2211.05927/) (2022)
- [Unsupervised Music Source Separation Using Differentiable Parametric Source Models](https://mlsanity.com/paper/2201.09592/) (2022)
- [Environmental Sound Extraction Using Onomatopoeic Words](https://mlsanity.com/paper/2112.00209/) (2021)
- [Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training](https://mlsanity.com/paper/2302.00286/) (2023)
- [AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries](https://mlsanity.com/paper/2104.13553/) (2021)
- [Unsupervised Source Separation via Bayesian Inference in the Latent Domain](https://mlsanity.com/paper/2110.05313/) (2021)
- [Selective Scene Text Removal](https://mlsanity.com/paper/2309.00410/) (2023)
- [User-guided Generative Source Separation](https://mlsanity.com/paper/2507.01339/) (2025)
- [Locate This, Not That: Class-Conditioned Sound Event DOA Estimation](https://mlsanity.com/paper/2203.04197/) (2022)
- [Metadata Improves Segmentation Through Multitasking Elicitation](https://mlsanity.com/paper/2308.09411/) (2023)
- [Improving Music Source Separation with Diffusion and Consistency Refinement](https://mlsanity.com/paper/2412.06965/) (2024)
- [Data-Driven Radio Propagation Modeling using Graph Neural Networks](https://mlsanity.com/paper/2501.06236/) (2025)
- [LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation](https://mlsanity.com/paper/2111.12516/) (2021)
- [SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech](https://mlsanity.com/paper/2206.12132/) (2022)
- [Proceedings of the 2nd International Workshop on Reading Music Systems](https://mlsanity.com/paper/2212.00380/) (2022)
- [Complete and separate: Conditional separation with missing target source attribute completion](https://mlsanity.com/paper/2307.14609/) (2023)
- [A Conditioned UNet for Music Source Separation](https://mlsanity.com/paper/2512.15532/) (2025)
- [Clean2FX: Label-conditioned modeling for clean-to-effect guitar audio transformations](https://mlsanity.com/paper/2607.08863/) (2026)

## Abstract (arXiv)

Data-driven models for audio source separation such as U-Net or Wave-U-Net are usually models dedicated to and specifically trained for a single task, e.g. a particular instrument isolation. Training them for various tasks at once commonly results in worse performances than training them for a single specialized task. In this work, we introduce the Conditioned-U-Net (C-U-Net) which adds a control mechanism to the standard U-Net. The control mechanism allows us to train a unique and generic U-Net to perform the separation of various instruments. The C-U-Net decides the instrument to isolate according to a one-hot-encoding input vector. The input vector is embedded to obtain the parameters that control Feature-wise Linear Modulation (FiLM) layers. FiLM layers modify the U-Net feature maps in order to separate the desired instrument via affine transformations. The C-U-Net performs different instrument separations, all with a single model achieving the same performances as the dedicated ones at a lower cost.