History: Two-channel mixtures of speech and real-world background noise
Comparing version 117 with version 123
|
@@ -Lines: 5-8 changed to +Lines: 5-12 @@
!!Introduction
This task aims to evaluate denoising and DOA estimation techniques by 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].
+
+ !! Results + *Results for the [http://www.onn.nii.ac.jp/sisec13/evaluation_result/BGN/homepage_BGN_dev.html|development dataset] + *Results for the [http://www.onn.nii.ac.jp/sisec13/evaluation_result/BGN/homepage_BGN_test.html|test dataset] !!Description of the dataset @@ -Lines: 17-22 changed to +Lines: 21-26 @@
* -+Sq2+-: square 2 (another square than Sq1)
and in two different positions within each environment:
- * -+Ce+-: center (except in -+Su1+- and -+Su2+-)
* -+Co+-: corner
+ * -+Ce+-: center
* -+Co+-: corner (except in -+Su1+- and -+Su2+-)
Two recordings identified by a letter (A or B) were made in each case. Mixtures were then generated by adding a speech signal to the background noise signal. For the reverberant environments -+Su+- and -+Ca+-, the speech signals were recorded in an office room using the same microphone pair. For the outdoor environment -+Sq+-, the speech signals were mixed anechoically through simulation. The distance between the sound source and the array centroid was 1.0 m for female speech and 0.8 m for male speech. The direction of arrival (DOA) of the speech source was different in each mixture and the signal-to-noise ratio (SNR) was drawn randomly between -17 and +12 dB.
@@ -Lines: 29-33 changed to +Lines: 33-37 @@
* -+<take>+-: take ( -+A+-, -+B+-)
!!Development data
- __Download the [http://www.irisa.fr/metiss/SiSEC11/noise/dev.zip|development set] (24 MB)__
+ __Download the [http://corpus-search.nii.ac.jp/sisec/2013/noise/dev.zip|development set] (11 MB)__
The data consists of 36 WAV audio files and 10 text files. These files are named as follows: |