数据介绍

Thedsd100is a dataset of 100 full lengths music tracks of different styles along with their isolateddrums,bass,vocalsandothersstems.

dsd100contains two folders, a folder with a training set: "train", composed of 50 songs, and a folder with a test set: "test", composed of 50 songs. Supervised approaches should be trained on the training set and tested on both sets.

For each file, the mixture correspond to the sum of all the signals. All signals are stereophonic and encoded at 44.1kHz.

The data fromdsd100consist of 100 tracks which are derived fromThe 'Mixing Secrets' Free Multitrack Download Library. Please refer to this original resource for any question regarding your rights on your use of the DSD100 data.

Have a look at thedetailed list of all tracks.

Download

@inproceedings{
  SiSEC16,
  Title = {The 2016 Signal Separation Evaluation Campaign},
  Address = {Cham},
  Author = {Liutkus, Antoine and St{\"o}ter, Fabian-Robert and Rafii, Zafar and Kitamura, Daichi and Rivet, Bertrand and Ito, Nobutaka and Ono, Nobutaka and Fontecave, Julie},
  Editor = {Tichavsk{\'y}, Petr and Babaie-Zadeh, Massoud and Michel, Olivier J.J. and Thirion-Moreau, Nad{\`e}ge},
  Pages = {323--332},
  Publisher = {Springer International Publishing},
  Year = {2017},
  booktitle = {Latent Variable Analysis and Signal Separation - 12th International Conference, {LVA/ICA} 2015, Liberec, Czech Republic, August 25-28, 2015, Proceedings},
}


Parsers

  • dsdtools: Python based dataset parser
  • dsd100mat: MATLAB scripts to parse and processdsd100.

Evaluation

  • bsseval: Matlab bases evaluation
  • SiSEC 2016: Signal Separation Evaluation Challenge 2016

Acknowledgements

We would like to thank Mike Senior not only for giving us the permission to use this multitrack material, but also for maintaining such resources for the audio community.

Authors

  • Zafar Rafii
  • Antoine Liutkus
  • Fabian-Robert Stöter
  • Stylianos Ioannis Mimilakis

Citation

If you use this dataset, please reference it accordingly: