Published August 28, 2013 | Version 1.0
Dataset Restricted

MASS: Music Audio Signal Separation


  • 1. Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain


This database was created to help to evaluate of Musical Audio Signal Separation algorithms and statements on a representative set of professionally produced music (i.e. real music recordings).

We include several song snips of a few seconds (10s-40s) with the following contents:

  • Tracks (with/without effects): Stereo Microsoft PCM WAV files (44.1Khz, 24 bits) of every instrumental track including and/or without including effects (plugins enabled or disabled in the project file used for production)
  • Description of the effects: When available, we include a description of the plugins used to modify the tracks without effects.
  • Lyrics: When available, lyrics are included.
  • License: All licenses allow these data sets to be used in scientific research but other may grant other priviledges (such as by-nc Creative Common licensed work).

Using this dataset

When the MASS dataset is used for academic research, we would highly appreciate if scientific publications of works partly based on the MASS dataset cite the following publication:

      author =  {Vinyes, M},
      title = { {MTG MASS database} },
      howpublished = {\\\url{} },
      year = {2008},

We are interested in knowing if you find our datasets useful! If you use our dataset please email us at and tell us about your research.



The record is publicly accessible, but files are restricted to users with access.

Request access

If you would like to request access to these files, please fill out the form below.

You need to satisfy these conditions in order for this request to be accepted:

Please include in the justification field your academic affiliation (if you have one) and a brief description of your research topics and why you would like to use this dataset. If you do not include this information we may not approve your request.

The dataset was compiled by M. Vinyes (MTG former member). We would like to thank Bearlin and Sargon for releasing the tracks of their songs and Sergi Vila at Garatge Produccions and Juan Pedro Barroso at Kcleta Studios for their effort to provide us what we requested. This work was in the scope of the current research on Audio Source Separation research area within the Music Technology Group (MTG) and was partially funded by SAME project (FP6-507142) 2008-2010.
Copyright © 2008 Music Technology Group, Universitat Pompeu Fabra. All Rights Reserved.
The MASS dataset is offered free of charge for internal non-commercial use only.  You may not redistribute, publically communicate or modify it, unless expressly permitted by the Universitat Pompeu Fabra (UPF) or by applicable law. The individual contents of the dataset may be protected by copyright, and a non-transferrable limited license to reproduce and use the same is granted for the indicated purpose only.
The dataset and its contents are made available on an “as is” basis and without warranties of any kind, including without limitation satisfactory quality and conformity, merchantability, fitness for a particular purpose, accuracy or completeness, or absence of errors. Subject to any liability that may not be excluded or limited by law, the UPF is not liable for, and expressly excludes, all liability for loss or damage however and whenever caused to anyone by any use of the MASS dataset or any part of it.

Personal data of users provided through using the Download form is processed in accordance with the following policy: Responsibility. The personal data provided will be stored in file called "Projectes de recerca, desenvolupament i innovació", under the responsibility of Universitat Pompeu Fabra.

PURPOSES. The data is processed for the general purpose of carrying out research development and innovation studies, works or projects. In particular, but without limitation, the data is processed for the purpose of communicating with Licensee regarding any administrative and legal / judicial purposes.

COLLECTION. We collect personal data including name, surname, affiliation and email address. Only the data marked with a star is obligatory. Users must provide true and accurate personal profile data. Users must NOT upload any sensitive data regarding racial origin, trade union membership, religion, ideology and sexual life, the user's or third party's health, or relative to the commission of criminal offences or proceedings and associated penalties or fines.

DISCLOSURE. The data is kept confidential and not communicated to anyone.

CONFIDENTIALITY. Technical and organizational measures have been adopted to preserve and protect users' personal information from unauthorized use or access and from being altered, lost or misused, taking into account the technological state of art, the features of the information stored and the risks to which information is exposed.

USER RIGHTS. Rights to access, correct, cancel or object to data in these files may be exercised by applying in writing, including a photocopy of your identity card or equivalent to: Gerent. Universitat Pompeu Fabra. Pl. de la Mercè, 12. 08002 - Barcelona.

CONSENT. By sending a contact form, users expressly agree to this policy, including the sending of electronic communications.

You are currently not logged in. Do you have an account? Log in here