Historique: Two-channel mixtures of speech and real-world background noise

Comparaison de la version 86 à la version 89


@@ -Lignes: 3-6 changées en +Lignes: 3-11 @@

This task aims at evaluating source separation and denoising techniques in the context of speech enhancement by merging two datasets: the [http://sisec2010.wiki.irisa.fr/tiki-index.php?page=Source+separation+in+the+presence+of+real-world+background+noise|SiSEC 2010 noisy speech dataset] and the [http://www.dcs.shef.ac.uk/spandh/chime/PCC/datasets.html|CHiME corpus]. Both datasets consist of two-channel mixtures of one speech source and real-world background noise, so that algorithms applicable to one dataset are applicable to the other without additional effort. The source separation results obtained over the latter dataset will be analyzed in line of the speech recognition results obtained over that dataset as part of the [http://www.dcs.shef.ac.uk/spandh/chime/challenge.html|CHiME Challenge].
+
+
+ !!Results
+
+ __See the results over [http://www.irisa.fr/metiss/SiSEC11/noise/results_test.html|test] and [http://www.irisa.fr/metiss/SiSEC11/noise/results_dev.html|development] data__


@@ -Lignes: 62-65 changées en +Lignes: 67-72 @@
* -+dev_<env>_<cond>_<take>_DOA.txt+-: DOA of the speech source (see the [http://sisec2010.wiki.irisa.fr/tiki-index.php?page=Source+separation+in+the+presence+of+real-world+background+noise|SiSEC 2010 wiki] for the convention adopted to measure DOA)
Since the source DOAs were measured geometrically in the -+Su+- and -+Ca+- environments, they might contain a measurement error up to a few degrees; on the contrary, there is no such error in the -+Sq+- environment.
+
+ The mixtures dev_Ca1_Co_A_mix.wav and dev_Ca1_Co_B_mix.wav are identical (this is a mistake that will be corrected in future evaluations).

Entrants wishing to exploit the context of each sentence in the domestic environment database can also __download the corresponding [http://www.irisa.fr/metiss/SiSEC11/noise/dev_embedded.zip|5 min recordings] (86 MB)__ (same nomenclature as above).

@@ -Lignes: 117-121 changées en +Lignes: 124-128 @@
The estimated speaker DOAs in task 1 will be evaluated in terms of absolute difference with the true DOAs.
- The estimated speech signals in task 2 will be evaluated via the energy ratio criteria defined in the [http://bass-db.gforge.inria.fr/bss_eval/|BSS_EVAL] toolbox allowing arbitrary filtering between the estimated source and the true source and via the perceptually-motivated criteria in the [http://bass-db.gforge.inria.fr/peass/PEASS-Software.html|PEASS] toolkit.
+ The estimated speech signals in task 2 will be evaluated via the energy ratio criteria defined in the [http://bass-db.gforge.inria.fr/bss_eval/|BSS_EVAL] toolbox allowing arbitrary filtering between the estimated source and the true source.

The estimated speech and noise spatial image signals in task 3 will be evaluated via the energy ratio criteria introduced for the [http://www.irisa.fr/metiss/SASSEC07/?show=criteria|Stereo Audio Source Separation Evaluation Campaign] and via the perceptually-motivated criteria in the [http://bass-db.gforge.inria.fr/peass/PEASS-Software.html|PEASS] toolkit.

Historique

Légende : v=afficher, c=comparer, d=différences
Date UtilisateurNote à propos de cette modification Version Action
mer. 21 de déc., 2011 16:16 CET admin   89
En cours
 v
jeu. 17 de nov., 2011 14:31 CET admin   88  v  c  d  
mer. 16 de nov., 2011 08:55 CET admin   87  v  c  d  
mar. 20 de sept., 2011 04:09 CEST admin   86  v  c  d  
ven. 12 de août, 2011 11:54 CEST admin   85  v  c  d  
ven. 12 de août, 2011 11:43 CEST admin   84  v  c  d  
ven. 12 de août, 2011 11:41 CEST admin   83  v  c  d  
ven. 12 de août, 2011 11:33 CEST admin   82  v  c  d  
ven. 12 de août, 2011 11:32 CEST admin   81  v  c  d  
ven. 12 de août, 2011 11:30 CEST admin   80  v  c  d  
ven. 12 de août, 2011 08:27 CEST admin   79  v  c  d  
jeu. 11 de août, 2011 15:17 CEST admin   78  v  c  d  

Menu

Rechercher avec Google

 
sisec2011.wiki.irisa.fr
WWW