History: Professionally produced music recordings
Comparing version 34 with version 40
|
@@ -Lines: 8-11 changed to +Lines: 8-16 @@
* Test and development data (test2 and dev2) of [http://sisec2010.wiki.irisa.fr/tiki-index.php|SiSEC 2010]
* New test data of SiSEC 2013 (test3)
+
+ !! Results + Results for the [http://www.onn.nii.ac.jp/sisec13/evaluation_result/MUS/devMUS2013.htm|development dataset]. + Results for the [http://www.onn.nii.ac.jp/sisec13/evaluation_result/MUS/testMUS2013.htm|test dataset]. +
!! Test Data
__Download [http://www.irisa.fr/metiss/SiSEC10/professional/test1.zip|test1.zip] (7 MB)__ (Test data of [http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Professionally+produced+music+recordings|SiSEC2008] ) @@ -Lines: 90-94 changed to +Lines: 95-99 @@
* vocals, drums, bass, other
__~np~test2__nine_inch_nails-the_good_soldier__snip_104_125__mix.wav~/np~__
- * bass, drums, vocals, other
+ * drums, vocals, other
__~np~test2__shannon_hurley-sunrise__snip_62_85__mix.wav~/np~__
* vocals, drums, bass, piano @@ -Lines: 115-131 changed to +Lines: 120-133 @@
Each participant should then send an email to "zbynek.koldovsky (at) tul.cz" and to "onono (at) nii.ac.jp" 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)
+ *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 same basic evaluation criteria as for the [./tiki-index.php?page=Underdetermined-+speech+and+music+mixtures|under-determined speech and music mixtures dataset] will be used first so that results are comparable. More precisely, the estimated stereo source signals will be evaluated via the criteria used for the [http://www.irisa.fr/metiss/SASSEC07/?show=criteria|Stereo Audio Source Separation Evaluation Campaign], except that the order of the sources is fixed. These criteria distinguish spatial (or filtering) distortion, interference and artifacts.
* Associated matlab code: [http://sisec2008.wiki.irisa.fr/tiki-download_file.php?fileId=17|bss_eval_images_nosort.m] Additional evaluation will be provided through the perceptual evaluation toolkit [http://bass-db.gforge.inria.fr/peass/|PEASS].
+ The evaluation will be done through the perceptual evaluation toolkit [http://bass-db.gforge.inria.fr/peass/|PEASS v.2.0].
!! Potential participants
- * MarC Nxx yz
+ * M. Nxx
* Vasileios Pantazis
* Alexey Ozerov (alexey.ozerov (a) irisa_fr) @@ -Lines: 141-143 changed to +Lines: 143-144 @@
[./tiki-index.php?page=Audio+source+separation|Back to Audio source separation top]
-
|