Open-Unmix - A Reference Implementation for Music Source Separation

Fabian-Robert Stöter 1 Stefan Uhlich 2 Antoine Liutkus 1 Yuki Mitsufuji 3
1 ZENITH - Scientific Data Management
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier, CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Music source separation is the task of decomposing music into its constitutive components, e.g., yielding separated stems for the vocals, bass, and drums. Such a separation has many applications ranging from rearranging/repurposing the stems (remixing, repanning, upmixing) to full extraction (karaoke, sample creation, audio restoration). Music separation has a long history of scientific activity as it is known to be a very challenging problem. In recent years, deep learning-based systems-for the first time-yielded high-quality separations that also lead to increased commercial interest. However, until now, no open-source implementation that achieves state-of-the-art results is available. Open-Unmix closes this gap by providing a reference implementation based on deep neural networks. It serves two main purposes. Firstly, to accelerate academic research as Open-Unmix provides implementations for the most popular deep learning frameworks, giving researchers a flexible way to reproduce results. Secondly, we provide a pre-trained model for end users and even artists to try and use source separation. Furthermore, we designed Open-Unmix to be one core component in an open ecosystem on music separation, where we already provide open datasets, software utilities, and open evaluation to foster reproducible research as the basis of future development.
Document type :
Journal articles
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal.inria.fr/hal-02293689
Contributor : Antoine Liutkus <>
Submitted on : Saturday, September 21, 2019 - 2:45:29 PM
Last modification on : Wednesday, October 9, 2019 - 2:28:03 PM

File

10.21105.joss.01667.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Fabian-Robert Stöter, Stefan Uhlich, Antoine Liutkus, Yuki Mitsufuji. Open-Unmix - A Reference Implementation for Music Source Separation. Journal of Open Source Software, Open Journals, 2019, The Journal of Open Source Software, 4 (41), pp.1667. ⟨10.21105/joss.01667⟩. ⟨hal-02293689⟩

Share

Metrics

Record views

190

Files downloads

412