Languages

QUASI Database – A musical audio signal Database for Source Separation

Quaero
QUASI, stands for QUaero Audio SIgnals, is a database dedicated to research on Music Information Retrieval.

This database has been gathered inside the QUAERO Project funded by the French agency OSEO.

 

This database is a joint work between the METISS team at INRIA/IRISA and the AAO team at Telecom-ParisTech.

 

Description :

QUASI-Separation is composed of 11 multitrack songs. The different songs are listed below (Artist – Song Name) :

  • Another Dreamer – One We Love
  • Carl Leth – The world is under attack
  • Alexq – Carol of the bells
  • Emily Hurst – Parting friends
  • Fort Minor – Remember the name
  • Glen Philips – The spirit of shackleton
  • Jims Big Ego – Mix tape
  • Nine Inch Nails – Good Soldier
  • Shannon Hurley – Sunrise
  • Ultimate nz tour
  • Vieux Farka Touré – Ana

 

These multi-track songs have been gathered by INRIA/IRISA Metiss team.

A sound engineer at Telecom-Paristech has produced several kind of mixes for each song.

The convention for the mix names is :

  • Bal: balance,
  • Pan: panoramic,
  • Eq: equalization,
  • Comp: dynamic compression,
  • Fx: various effects,
  • Comp+: « master » dynamic compression.

 

Licenses :

  • Another Dreamer – One We Love : Creative Commons Attribution-NonCommercial 1.0
  • Carl Leth – The world is under attack : Creative Commons Attribution-ShareAlike 1.0
  • Alexq – Carol of the bells : Creative Commons Attribution-NonCommercial-ShareAlike 2.0
  • Emily Hurst – Parting friends : Creative Commons Attribution-ShareAlike 1.0
  • Fort Minor – Remember the name : Creative Commons Attribution-NonCommercial 2.5
  • Glen Philips – The spirit of shackleton : Creative Commons Attribution 3.0
  • Jims Big Ego – Mix tape : Creative Commons Attribution-ShareAlike 1.0
  • Nine Inch Nails – Good Soldier : License
  • Shannon Hurley – Sunrise : Creative Commons Attribution-NonCommercial 3.0
  • Ultimate nz tour : Creative Commons Attribution-Noncommercial-ShareAlike 3.0
  • Vieux Farka Touré – Ana : Creative Commons Attribution-NonCommercial 2.5

 

Contributors :

At Telecom-ParisTech :

  • Michel Desnoues
  • Jean-Louis Durrieu
  • Thomas Fillon
  • Gaël Richard

At INRIA/IRISA :

  • Olivier Le Blouch
  • Emmanuel Vincent

 

Download :

Before downloading the database, you have to agree on the terms of the license for each song as listed above.

  Download QUASI

 

Contacts : Thomas Fillon and Gaël Richard (firstname.lastname@telecom-paristech.fr)

 

References using this database:

  • Emmanuel Vincent, Shoko Araki, Fabian J. Theis, Guido Nolte, Pau Bofill, Hiroshi Sawada, Alexey Ozerov, B. Vikrham Gowreesunker, Dominik Lutter, and Ngoc Q.K. Duong, “The Signal Separation Evaluation Campaign (2007-2010): Achievements and Remaining Challenges”, Signal Processing 92, pp. 1928-1936, 2012.
  • Antoine Liutkus, Roland Badeau, and Gaël Richard, “Gaussian Processes for Underdetermined Source Separation“, IEEE Transactions on Signal Processing, vol. 59-7, p3155-3167,2011.

 

 

Institut Mines-Telecom            Telecom-Paristech            INRIA            IRISA

 

Comments are closed.