Skip to Main content Skip to Navigation
Conference papers

CONDITIONED-U-NET: INTRODUCING A CONTROL MECHANISM IN THE U-NET FOR MULTIPLE SOURCE SEPARATIONS

Gabriel Meseguer-Brocal 1, 2 Geoffroy Peeters 3, 4, 5
1 Analyse et synthèse sonores;
STMS - Sciences et Technologies de la Musique et du Son, IRCAM - Institut de Recherche et Coordination Acoustique/Musique
5 S2A - Signal, Statistique et Apprentissage
LTCI - Laboratoire Traitement et Communication de l'Information
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02448917
Contributor : Gabriel Meseguer Brocal <>
Submitted on : Wednesday, January 22, 2020 - 3:35:21 PM
Last modification on : Wednesday, October 14, 2020 - 3:58:48 AM
Long-term archiving on: : Thursday, April 23, 2020 - 5:02:58 PM

File

1907.01277.pdf
Files produced by the author(s)

Identifiers

Citation

Gabriel Meseguer-Brocal, Geoffroy Peeters. CONDITIONED-U-NET: INTRODUCING A CONTROL MECHANISM IN THE U-NET FOR MULTIPLE SOURCE SEPARATIONS. Proceedings of the 20th International Society for Music Information Retrieval Conference, Nov 2019, Delft, Netherlands. ⟨10.5281/zenodo.3527766⟩. ⟨hal-02448917⟩

Share

Metrics

Record views

47

Files downloads

40