History: Underdetermined speech and music mixtures
Comparing version 23 with version 33
|
@@ -Lines: 1-11 changed to +Lines: 1-15 @@
!::Underdetermined-speech and music mixtures::
- We propose to repeat the [http://sisec2011.wiki.irisa.fr/tiki-index.php?page=Underdetermined+speech+and+music+mixtures|underdetermined-speech and music mixtures] task in SiSEC2011.
+ We propose to repeat the [http://sisec2011.wiki.irisa.fr/tiki-index.php?page=Underdetermined+speech+and+music+mixtures|underdetermined-speech and music mixtures task in SiSEC2011].
!Results Results for development sets: [http://www.onn.nii.ac.jp/sisec13/evaluation_result/UND/underdetermined_dev1_all.html|dev1], [http://www.onn.nii.ac.jp/sisec13/evaluation_result/UND/underdetermined_dev2_all.html|dev2], [http://www.onn.nii.ac.jp/sisec13/evaluation_result/UND/underdetermined_dev3_all.html|dev3]. Results for test sets: [http://www.onn.nii.ac.jp/sisec13/evaluation_result/UND/underdetermined_test_all.html|test], [http://www.onn.nii.ac.jp/sisec13/evaluation_result/UND/underdetermined_test2_all.html|test2], [http://www.onn.nii.ac.jp/sisec13/evaluation_result/UND/underdetermined_test3_all.html|test3]. !! Test data We have three datasets:
- __Download [http://www.irisa.fr/metiss/SiSEC10/underdetermined/test.zip|test.zip] (22 MB)__ (former test data of [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures|SiSEC2008].)
__Download [http://www.irisa.fr/metiss/SiSEC10/underdetermined/test2.zip|test2.zip] (16 MB)__ (former test data of [http://sisec2010.wiki.irisa.fr/tiki-index.php?page=Underdetermined-+speech+and+music+mixtures|SiSEC2010].) __Download [http://www.irisa.fr/metiss/SiSEC11/underdetermined/test3.zip|test3.zip] (8.6MB)__(~~red:fresh~~ data for SiSEC2011. This is the 3-ch mixtures of 4 speech sources.)
+ __Download [http://www.irisa.fr/metiss/SiSEC10/underdetermined/test.zip|test.zip] (22 MB)__ (test data of [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures|SiSEC2008].)
__Download [http://www.irisa.fr/metiss/SiSEC10/underdetermined/test2.zip|test2.zip] (16 MB)__ (test data of [http://sisec2010.wiki.irisa.fr/tiki-index.php?page=Underdetermined-+speech+and+music+mixtures|SiSEC2010].) __Download [http://www.irisa.fr/metiss/SiSEC11/underdetermined/test3.zip|test3.zip] (8.6MB)__(test data of [http://sisec2011.wiki.irisa.fr/tiki-index.php?page=Underdetermined%20speech%20and%20music%20mixtures|SiSEC2011]. This is the 3-ch mixtures of 4 speech sources.) !!!test.zip @@ -Lines: 13-17 changed to +Lines: 17-21 @@
*__instantaneous mixtures__ (static sources scaled by positive gains)
*__live recordings__ (static sources played through loudspeakers in a meeting room, recorded one at a time by a pair of omnidirectional microphones and subsequently added together)
- **__CAUTION__: For SiSEC2011, we will ~~red:NOT~~ evaluate "__synthetic convolutive mixtures__" (static sources filtered by synthetic room impulse responses simulating a pair of omnidirectional microphones via the Roomsim toolbox).
+ **__CAUTION__: For SiSEC2013, we will ~~red:NOT~~ evaluate "__synthetic convolutive mixtures__" (static sources filtered by synthetic room impulse responses simulating a pair of omnidirectional microphones via the Roomsim toolbox).
The room dimensions are the same for synthetic convolutive mixtures and live recordings (4.45 x 3.55 x 2.5 m). The reverberation time is set to either 130 ms or 250 ms and the distance between the two microphones to either 5 cm or 1 m, resulting in 9 mixing conditions overall. @@ -Lines: 50-54 changed to +Lines: 54-57 @@
__Licensing Issue:__ These files are made available under the terms of the Creative Commons [http://creativecommons.org/licenses/by-nc-sa/2.0/|Attribution-NonCommercial-ShareAlike 2.0] license. The authors are Shannon Hurley, Nine Inch Nails, AlexQ (Alexander Lozupone), Mokamed, Carl Leth and Jim's Big Ego for music source signals and Hiroshi Sawada for mixture signals.
-
!!!test3.zip @@ -Lines: 66-77 changed to +Lines: 69-78 @@
__Licensing Issue:__ These files are made available under the terms of the Creative Commons [http://creativecommons.org/licenses/by-nc-sa/2.0/|Attribution-NonCommercial-ShareAlike 2.0] license. The author is Shoko Araki for mixture signals.
-
!! Development data
-
__Download [http://www.irisa.fr/metiss/SiSEC10/underdetermined/dev1.zip|dev1.zip] (91 MB)__
__Download [http://www.irisa.fr/metiss/SiSEC10/underdetermined/dev2.zip|dev2.zip] (47 MB)__
- (Both are the former development data of [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures|SiSEC2008] and [http://sisec2010.wiki.irisa.fr/tiki-index.php?page=Underdetermined-+speech+and+music+mixtures|SiSEC2010])
+ __Download [http://www.irisa.fr/metiss/SiSEC11/underdetermined/dev3.zip|dev3.zip] (47 MB)__
(The former development data of [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures|SiSEC2008], [http://sisec2010.wiki.irisa.fr/tiki-index.php?page=Underdetermined-+speech+and+music+mixtures|SiSEC2010] and [http://sisec2011.wiki.irisa.fr/tiki-index.php?page=Underdetermined%20speech%20and%20music%20mixtures|SiSEC2011].) The data consist of Matlab MAT-files and WAV audio files, that can be imported in Matlab using the commands load and wavread respectively. These files are named as follows: @@ -Lines: 85-89 changed to +Lines: 86-89 @@
where <srcset> is a shortcut for the set of source signals, <mixtype> for a shortcut for the mixture type, <reverb> the reverberation time, <spacing> the microphone spacing and <j> the source index.
-
All mixture signals and source image signals have 10s duration. Music source signals have 11s duration to avoid border effects within convolutive mixtures. The last 10s are then selected once the mixing system has been applied. @@ -Lines: 98-119 changed to +Lines: 98-114 @@
*dev3_<srcset>_<mixtype>_<reverb>_<spacing>_sim_<j>.wav: stereo contribution of a source signal to the two mixture channels
*dev3_<srcset>_<mixtype>_<reverb>_<spacing>_mix.wav: stereo mixture signal
-
__Licensing issue: __ These files are made available under the terms of the Creative Commons [http://creativecommons.org/licenses/by-nc-sa/2.0/|Attribution-NonCommercial-ShareAlike 2.0] license. The authors are Another Dreamer and Alex Q for music source signals and Hiroshi Sawada, Shoko Araki and Emmanuel Vincent for mixture signals.
-
!! Tasks
- The source separation problem has been split into four tasks:
+ The source separation problem has been split into three tasks:
## __source counting__ (estimate the number of sources)
## __source signal estimation__ (estimate the mono source signals) ## __source spatial image estimation__ (estimate the stereo contribution of each source to the two mixture channels)
-
!! Submissions
-
Each participant is asked to submit the results of his/her algorithm for tasks 2 and/or 3
* over all or part of "test", "test2" and "test3".
- * over all or part of "dev2", if his/her algorithm was not previously submitted to the [http://www.irisa.fr/metiss/SASSEC07/|Stereo Audio Source Separation Evaluation Campaign] nor [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures|SiSEC2008], so as to assess improvements compared to that campaign.
*and all or part of "dev3".
+ * over all or part of "dev2" and "dev3", if his/her algorithm was not previously submitted to the [http://www.irisa.fr/metiss/SASSEC07/|Stereo Audio Source Separation Evaluation Campaign], [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures|SiSEC2008], [http://sisec2010.wiki.irisa.fr/tiki-index.php?page=Underdetermined-+speech+and+music+mixtures|SiSEC2010] nor [http://sisec2011.wiki.irisa.fr/tiki-index.php?page=Underdetermined%20speech%20and%20music%20mixtures|SiSEC2011], so as to assess improvements compared to those campaigns.
The results for task 1 may also be submitted. @@ -Lines: 137-148 changed to +Lines: 132-140 @@
Note that the submitted audio files will be made available on a website under the terms of the Creative Commons [http://creativecommons.org/licenses/by-nc-sa/2.0/|Attribution-NonCommercial-ShareAlike 2.0] license.
-
!! Reference software
-
Please refer the [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures|previous SiSEC2008 page].
!! Evaluation criteria
-
We propose to use the same evaluation criteria as in SiSEC 2010, except that the order of the estimated sources must be recovered.
|