1. Open-Unmix - A Reference Implementation for Music Source Separation
- Author
-
Stefan Uhlich, Antoine Liutkus, Fabian-Robert Stöter, Yuki Mitsufuji, Scientific Data Management (ZENITH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Sony Stuttgart Technology Center (STC Sony), Sony Deutschland GmbH, Sony Corporation, ANR-15-CE38-0003,KAMoulox,Démixage en ligne de larges archives sonores(2015), and Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Inria Sophia Antipolis - Méditerranée (CRISAM)
- Subjects
Multimedia ,Computer science ,End user ,business.industry ,Audio restoration ,Deep learning ,020206 networking & telecommunications ,02 engineering and technology ,Python (programming language) ,computer.software_genre ,030507 speech-language pathology & audiology ,03 medical and health sciences ,[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing ,0202 electrical engineering, electronic engineering, information engineering ,Source separation ,Artificial intelligence ,Reference implementation ,0305 other medical science ,business ,Implementation ,computer ,Repurposing ,computer.programming_language - Abstract
International audience; 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.
- Published
- 2019
- Full Text
- View/download PDF