MUSDB18 - a corpus for music separation

Abstract : The sigsep musdb18 data set consists of a total of 150 full-track songs of different styles and includes both the stereo mixtures and the original sources, divided between a training subset and a test subset. Its purpose is to serve as a reference database for the design and the evaluation of source separation algorithms. The objective of such signal processing methods is to estimate one or more sources from a set of mixtures, e.g. for karaoke applications. It has been used as the official dataset in the professionally-produced music recordings task for SiSEC 2018, which is the international campaign for the evaluation of source separation algorithms.
Document type :
Other publications
Complete list of metadatas

https://hal.inria.fr/hal-02190845
Contributor : Antoine Liutkus <>
Submitted on : Tuesday, July 30, 2019 - 10:00:59 AM
Last modification on : Saturday, October 12, 2019 - 1:18:02 PM

File

musdb.pdf
Files produced by the author(s)

Licence


Copyright

Identifiers

Collections

Citation

Zafar Rafii, Antoine Liutkus, Fabian Robert-Stöter, Stylianos Ioannis Mimilakis, Rachel Bittner. MUSDB18 - a corpus for music separation. 2017, ⟨10.5281/zenodo.1117371⟩. ⟨hal-02190845⟩

Share

Metrics

Record views

160

Files downloads

601