Professionally produced music recordings


We propose to repeat the Professionally produced music recordings (external link) task of SiSEC2011 with several new songs.

The task includes the following data:


Results for the development dataset (external link).
Results for the test dataset (external link).

Test Data

Download (external link) (7 MB) (Test data of SiSEC2008 (external link) )
Download (external link) (9 MB) (Test data of SiSEC 2010 (external link))
Download (external link) (79 MB) (full-length recordings for SiSEC2010)
Download (external link) (7 MB) (Test data of SiSEC 2013)
Download (external link) (59 MB) (full-length recordings for SiSEC2013)

The data consist of stereo WAV audio files that can be imported into Matlab using the wavread command. These files are named {test1,test2,test3}__[<author>]-[<song>]__{snip, full_mix}__{mix}.wav , where <author> is the author name and <song> is the song name.

The data include the following mixtures (snips and full-length recordings):

  • test1__tamy-que_pena_tanto_faz__snip__mix.wav
  • test1__bearlin-roads__snip__mix.wav
  • test2__glen_philips-the_spirit_of_shackleton__snip_163_185__mix.wav
  • test2__nine_inch_nails-the_good_soldier__snip_104_125__mix.wav
  • test2__shannon_hurley-sunrise__snip_62_85__mix.wav
  • test2__glen_philips-the_spirit_of_shackleton__full_mix.wav
  • test2__nine_inch_nails-the_good_soldier__full_mix.wav
  • test2__shannon_hurley-sunrise__full_mix.wav
  • test3__jims_big_ego-mix_tape__snip__mix.wav
  • test3__vieux_farka_toure-ana__snip__mix.wav
  • test3__jims_big_ego-mix_tape__full_mix__mix.wav
  • test3__vieux_farka_toure-ana__full_mix__mix.wav

Development Data

Download (external link) (22 MB) (Development data of SiSEC 2008 (external link))
Download (external link) (36 MB) (Development data of SiSEC 2010 (external link))
Download (external link) (75 MB) (full-length recordings for SiSEC2010 data)

The data consist of stereo WAV audio files, that can be imported in Matlab using the wavread command. These files are named {dev1,dev2}__ [ <author> ] - [ <song> ]__[ <snip> ]__ {mix,full_mix,<track>}.wav, where <author> is the author name, <song> is the song name, <snip> is a shortcut for snip information, and <track> is the separated track name (e.g., "vocals", "bass", etc.).

The data include the following mixtures (snips and full-length recordings):

  • dev1__bearlin-roads__snip_85_99__mix.wav
  • dev1__tamy-que_pena_tanto_faz__snip_6_19__mix.wav
  • dev2__another_dreamer-the_ones_we_love__snip_69_94__mix.wav
  • dev2__fort_minor-remember_the_name__snip_54_78__mix.wav
  • dev2__ultimate_nz_tour__snip_43_61__mix.wav
  • dev2__another_dreamer-the_ones_we_love__full_mix.wav
  • dev2__fort_minor-remember_the_name__full_mix.wav
  • dev2__ultimate_nz_tour__full_mix.wav

Separated tracks (needed for evaluation in dev1 and dev2) are in the corresponding folders named {dev1,dev2}__[<author>]-[<song>]__<snip>__<track>.wav .


All audio files are distributed under the terms different licenses, as listed below for each recodring:

The data were taken from the MTG MASS database (external link) and from the QUASI database (external link).


The following should be taken in to account:
  • The participants are encouraged to separate only the snips of songs in case of test1, test2, dev1, and dev2. In case of test3, the participants are encouraged to separate both snips and full-length recordings.
  • Some track names below have the following meaning:
    • "vocals" = "a sum of any singing including main vocal, back vocals and singing in the reverb"
    • "drums" = "a sum of any drums including bass drum, hi-hat, snare etc."
    • "bass" = "bass guitar only (i.e., not bass drum)"

Tracks to separate (test tasks)

  • vocals, guitar
  • vocals, bass, drums, piano
  • vocals, drums, bass, other
  • drums, vocals, other
  • vocals, drums, bass, piano
test3__jims_big_ego-mix_tape__{snip, full_mix}__mix.wav
  • vocals, drums, bass, other
test3__vieux_farka_toure-ana__{snip, full_mix}__mix
  • vocals, drums, bass, other

Tracks to separate (development tasks)

  • vocals, drums, guitar
  • vocals, drums, bass, claps
  • vocals, drums, bass


Participants may submit separation results for any above-mentioned tracks of the test and development mixtures.
In addition, each participant is asked to provide basic information about his/her algorithm (e.g. a bibliographical reference) and to declare its average running time, expressed in seconds per test excerpt and per GHz of CPU.

How to submit

Each participant should make his results available online in the form of a tarball called <YourName>_<dataset>.zip.
The included files must be named as follows:
<dataset><author>-<song><snip or full_mix>__<trackname>.wav
where <dataset> is one of the test/test2/dev2, <filename> is a shortcut for the set of source signals, <trackname> is the name of the extracted track. For example, the estimated vocal track for the task file "test2_glen_philips-the_spirit_of_shackleton_snip_163_185_mix.wav" should be named as "test2glen_philips-the_spirit_of_shackletonsnip_163_185__vocals.wav".

Each participant should then send an email to "zbynek.koldovsky (at)" and to "onono (at)" providing:
  • contact information (name, affiliation)
  • basic information about his/her algorithm, including its average running time (in seconds per test excerpt and per GHz of CPU) and a bibliographical reference if possible
  • the URL of the tarball(s)

The submitted audio files will be made available on a website under the terms of the same license as indicated in the section Licenses above. In other words, any modified version inherit exactly the same license as the original.

Evaluation criteria

The evaluation will be done through the perceptual evaluation toolkit PEASS v.2.0 (external link).

Potential participants

  • M. Nxx
  • Vasileios Pantazis
  • Alexey Ozerov (alexey.ozerov (a) irisa_fr)
  • Jeanlouis Durrieu (durrieu (a) enst_fr)
  • Maximo Cobos (mcobos (a) iteam_upv_es)
  • Pablo Cancela (pcancela (a)
  • Antoine Liutkus (antoine.liutkus (a)
  • Pierre Leveau (pierre.leveau (a)
  • Jordi Janer (jordi.janer (a)
  • Nobutaka Ono (onono (a)
  • Stanislaw Gorlow
Task proposed by Audio Committee

Back to Audio source separation top


Google Search