Main.TestDMS History

Hide minor edits - Show changes to markup

May 05, 2010, at 04:59 PM by 129.102.21.30 -

Added lines 1-471:

(:input form "http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/cookbook/post2mail.php" :)

Voice Conversion

Goal of this subjective test

The goal of this subjective test is to evaluate different methods used for converting a source voice into a target voice. The language of the speech utterances used in this test will be French but you can participate to this test even if you are not a French speaker. The method will transform only the timbre qualities of one voice so that it resembles another one. The prosodic characteristics will not be modified.

In this evaluation we will test the conversion of the voice of a french speaker into the voice of 2 differents speakers with differents accent (hispanic and french canadian). For each conversion, 2 test will be made, one about the proximity of the converted voice to the target and one about the quality of the conversion.

It should take you between 5 and 10 minutes to complete the test.

By completing this short questionnaire you are contributing to research on voice conversion, carried out at the Analysis Synthesis team of IRCAM.

Thanks in advance !

Pierre

First voice conversion

We want to evaluate the conversion from a Voice A to an other Voice B with a hispanic accent.

Here you can find example utterances of two different speakers voices:

The source Voice A :

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr bgcolor=#cccc99 align=center:) A (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-20.mp3 width=22 height=18:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-21.mp3 width=22 height=18:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-23.mp3 width=22 height=18:) (:tableend:)

The target Voice B :

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr bgcolor=#cccc09 align=center:) B (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Ex-20.mp3 width=22 height=18:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Ex-21.mp3 width=22 height=18:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Ex-23.mp3 width=22 height=18:) (:tableend:)

Please listen to them in order to get familiar to their different timbre qualities.

Now, for each of the following file, vote whether it is perceived as closer to the Voice A or to the Voice B.

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr bgcolor=#cccc99 align=center:) A (:cell align=left:) Perceived as voice A (:cellnr bgcolor=#cccc79 align=center:) <- (:cell align=left:) Perceived as closer to voice A (:cellnr bgcolor=#cccc59 align=center:) 0 (:cell align=center:) Perceived as between voice A and voice B (:cellnr bgcolor=#cccc29 align=left:) -> (:cell align=left:) Perceived as closer to voice B (:cellnr bgcolor=#cccc09 align=center:) B (:cell align=left:) Perceived as voice B (:tableend:)

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr align=center:) File (:cell bgcolor=#cccc99 align=center:) A (:cell bgcolor=#cccc79 align=center:) <- (:cell bgcolor=#cccc59 align=center:) 0 (:cell bgcolor=#cccc29 align=center:) -> (:cell bgcolor=#cccc09 align=center:) B (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-4.mp3 width=62 height=18:) (:cell align=center:) (:input radio Xa-Ex-4b A-Xa-Ex-4b#-2:) (:cell align=center:) (:input radio Xa-Ex-4b A-Xa-Ex-4b#-1:) (:cell align=center:) (:input radio Xa-Ex-4b A-Xa-Ex-4b#0:) (:cell align=center:) (:input radio Xa-Ex-4b A-Xa-Ex-4b#+1:) (:cell align=center:) (:input radio Xa-Ex-4b A-Xa-Ex-4b#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Ex-2.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Ex-2 A-Fe-Ex-2#-2:) (:cell align=center:) (:input radio Fe-Ex-2 A-Fe-Ex-2#-1:) (:cell align=center:) (:input radio Fe-Ex-2 A-Fe-Ex-2#0:) (:cell align=center:) (:input radio Fe-Ex-2 A-Fe-Ex-2#+1:) (:cell align=center:) (:input radio Fe-Ex-2 A-Fe-Ex-2#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-82.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Mul-82 A-Fe-Mul-82#-2:) (:cell align=center:) (:input radio Fe-Mul-82 A-Fe-Mul-82#-1:) (:cell align=center:) (:input radio Fe-Mul-82 A-Fe-Mul-82#0:) (:cell align=center:) (:input radio Fe-Mul-82 A-Fe-Mul-82#+1:) (:cell align=center:) (:input radio Fe-Mul-82 A-Fe-Mul-82#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-71.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Sin-71 A-Fe-Sin-71#-2:) (:cell align=center:) (:input radio Fe-Sin-71 A-Fe-Sin-71#-1:) (:cell align=center:) (:input radio Fe-Sin-71 A-Fe-Sin-71#0:) (:cell align=center:) (:input radio Fe-Sin-71 A-Fe-Sin-71#+1:) (:cell align=center:) (:input radio Fe-Sin-71 A-Fe-Sin-71#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Ex-6.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Ex-6 A-Fe-Ex-6#-2:) (:cell align=center:) (:input radio Fe-Ex-6 A-Fe-Ex-6#-1:) (:cell align=center:) (:input radio Fe-Ex-6 A-Fe-Ex-6#0:) (:cell align=center:) (:input radio Fe-Ex-6 A-Fe-Ex-6#+1:) (:cell align=center:) (:input radio Fe-Ex-6 A-Fe-Ex-6#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-3.mp3 width=62 height=18:) (:cell align=center:) (:input radio Xa-Ex-3b A-Xa-Ex-3b#-2:) (:cell align=center:) (:input radio Xa-Ex-3b A-Xa-Ex-3b#-1:) (:cell align=center:) (:input radio Xa-Ex-3b A-Xa-Ex-3b#0:) (:cell align=center:) (:input radio Xa-Ex-3b A-Xa-Ex-3b#+1:) (:cell align=center:) (:input radio Xa-Ex-3b A-Xa-Ex-3b#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-71.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Mul-71 A-Fe-Mul-71#-2:) (:cell align=center:) (:input radio Fe-Mul-71 A-Fe-Mul-71#-1:) (:cell align=center:) (:input radio Fe-Mul-71 A-Fe-Mul-71#0:) (:cell align=center:) (:input radio Fe-Mul-71 A-Fe-Mul-71#+1:) (:cell align=center:) (:input radio Fe-Mul-71 A-Fe-Mul-71#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-171.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Sin-171 A-Fe-Sin-171#-2:) (:cell align=center:) (:input radio Fe-Sin-171 A-Fe-Sin-171#-1:) (:cell align=center:) (:input radio Fe-Sin-171 A-Fe-Sin-171#0:) (:cell align=center:) (:input radio Fe-Sin-171 A-Fe-Sin-171#+1:) (:cell align=center:) (:input radio Fe-Sin-171 A-Fe-Sin-171#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Ex-5.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Ex-5 A-Fe-Ex-5#-2:) (:cell align=center:) (:input radio Fe-Ex-5 A-Fe-Ex-5#-1:) (:cell align=center:) (:input radio Fe-Ex-5 A-Fe-Ex-5#0:) (:cell align=center:) (:input radio Fe-Ex-5 A-Fe-Ex-5#+1:) (:cell align=center:) (:input radio Fe-Ex-5 A-Fe-Ex-5#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-7.mp3 width=62 height=18:) (:cell align=center:) (:input radio Xa-Ex-7b A-Xa-Ex-7b#-2:) (:cell align=center:) (:input radio Xa-Ex-7b A-Xa-Ex-7b#-1:) (:cell align=center:) (:input radio Xa-Ex-7b A-Xa-Ex-7b#0:) (:cell align=center:) (:input radio Xa-Ex-7b A-Xa-Ex-7b#+1:) (:cell align=center:) (:input radio Xa-Ex-7b A-Xa-Ex-7b#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-82.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Sin-82 A-Fe-Sin-82#-2:) (:cell align=center:) (:input radio Fe-Sin-82 A-Fe-Sin-82#-1:) (:cell align=center:) (:input radio Fe-Sin-82 A-Fe-Sin-82#0:) (:cell align=center:) (:input radio Fe-Sin-82 A-Fe-Sin-82#+1:) (:cell align=center:) (:input radio Fe-Sin-82 A-Fe-Sin-82#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-171.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Mul-171 A-Fe-Mul-171#-2:) (:cell align=center:) (:input radio Fe-Mul-171 A-Fe-Mul-171#-1:) (:cell align=center:) (:input radio Fe-Mul-171 A-Fe-Mul-171#0:) (:cell align=center:) (:input radio Fe-Mul-171 A-Fe-Mul-171#+1:) (:cell align=center:) (:input radio Fe-Mul-171 A-Fe-Mul-171#+2:) (:tableend:)

We now ask you to listen to and compare a pair of short utterances and decide which of the two utterances is perceived as more natural by attending to sound quality, i.e., presenting less sound degradation.

1. For each line on the tab, listen carefully to File 1 and File 2. Both sounds will correspond to the same source-target conversion, but processed by using slightly different methods. The differences requires careful listening so please use headphones if you can.

2. Then give a preference score about according to the following grades tab:

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr align=center:)Much better (:cell align=center:) +3 (:cellnr align=center:) Better (:cell align=center:) +2 (:cellnr align=center:) Slightly better (:cell align=center:) +1 (:cellnr align=center:) About the same (:cell align=center:) 0 (:tableend:)

to the left if you prefer File 1
to the right if you prefer File 2.

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr bgcolor=#cccc99 align=center:) File 1 (:cell bgcolor=#cccc99 align=center:) +3 (:cell bgcolor=#cccc89 align=center:) +2 (:cell bgcolor=#cccc79 align=center:) +1 (:cell bgcolor=#cccc59 align=center:) 0 (:cell bgcolor=#cccc39 align=center:) +1 (:cell bgcolor=#cccc19 align=center:) +2 (:cell bgcolor=#cccc09 align=center:) +3 (:cell bgcolor=#cccc09 align=center:) File 2 (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-88.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Sin-88/Fe-Mul-88 B-Fe-Sin-88#+3:) (:cell align=center:) (:input radio Fe-Sin-88/Fe-Mul-88 B-Fe-Sin-88#+2:) (:cell align=center:) (:input radio Fe-Sin-88/Fe-Mul-88 B-Fe-Sin-88#+1:) (:cell align=center:) (:input radio Fe-Sin-88/Fe-Mul-88 B-Fe-Sin-88#0:) (:cell align=center:) (:input radio Fe-Sin-88/Fe-Mul-88 B-Fe-Sin-88#-1:) (:cell align=center:) (:input radio Fe-Sin-88/Fe-Mul-88 B-Fe-Sin-88#-2:) (:cell align=center:) (:input radio Fe-Sin-88/Fe-Mul-88 B-Fe-Sin-88#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-88.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-99.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Sin-71/Fe-Mul-99 B-Fe-Sin-99#+3:) (:cell align=center:) (:input radio Fe-Sin-71/Fe-Mul-99 B-Fe-Sin-99#+2:) (:cell align=center:) (:input radio Fe-Sin-71/Fe-Mul-99 B-Fe-Sin-99#+1:) (:cell align=center:) (:input radio Fe-Sin-71/Fe-Mul-99 B-Fe-Sin-99#0:) (:cell align=center:) (:input radio Fe-Sin-71/Fe-Mul-99 B-Fe-Sin-99#-1:) (:cell align=center:) (:input radio Fe-Sin-71/Fe-Mul-99 B-Fe-Sin-99#-2:) (:cell align=center:) (:input radio Fe-Sin-71/Fe-Mul-99 B-Fe-Sin-99#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-99.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-11.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Mul-11/Fe-Sin-11 B-Fe-Mul-11#+3:) (:cell align=center:) (:input radio Fe-Mul-11/Fe-Sin-11 B-Fe-Mul-11#+2:) (:cell align=center:) (:input radio Fe-Mul-11/Fe-Sin-11 B-Fe-Mul-11#+1:) (:cell align=center:) (:input radio Fe-Mul-11/Fe-Sin-11 B-Fe-Mul-11#0:) (:cell align=center:) (:input radio Fe-Mul-11/Fe-Sin-11 B-Fe-Mul-11#-1:) (:cell align=center:) (:input radio Fe-Mul-11/Fe-Sin-11 B-Fe-Mul-11#-2:) (:cell align=center:) (:input radio Fe-Mul-11/Fe-Sin-11 B-Fe-Mul-11#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-11.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-8.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Mul-8/Fe-Sin-8 B-Fe-Mul-8#+3:) (:cell align=center:) (:input radio Fe-Mul-8/Fe-Sin-8 B-Fe-Mul-8#+2:) (:cell align=center:) (:input radio Fe-Mul-8/Fe-Sin-8 B-Fe-Mul-8#+1:) (:cell align=center:) (:input radio Fe-Mul-8/Fe-Sin-8 B-Fe-Mul-8#0:) (:cell align=center:) (:input radio Fe-Mul-8/Fe-Sin-8 B-Fe-Mul-8#-1:) (:cell align=center:) (:input radio Fe-Mul-8/Fe-Sin-8 B-Fe-Mul-8#-2:) (:cell align=center:) (:input radio Fe-Mul-8/Fe-Sin-8 B-Fe-Mul-8#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-8.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-38.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Sin-38/Fe-Mul-38 B-Fe-Sin-38#+3:) (:cell align=center:) (:input radio Fe-Sin-38/Fe-Mul-38 B-Fe-Sin-38#+2:) (:cell align=center:) (:input radio Fe-Sin-38/Fe-Mul-38 B-Fe-Sin-38#+1:) (:cell align=center:) (:input radio Fe-Sin-38/Fe-Mul-38 B-Fe-Sin-38#0:) (:cell align=center:) (:input radio Fe-Sin-38/Fe-Mul-38 B-Fe-Sin-38#-1:) (:cell align=center:) (:input radio Fe-Sin-38/Fe-Mul-38 B-Fe-Sin-38#-2:) (:cell align=center:) (:input radio Fe-Sin-38/Fe-Mul-38 B-Fe-Sin-38#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-38.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Sin-184.mp3 width=62 height=18:) (:cell align=center:) (:input radio Fe-Sin-184/Fe-Mul-184 B-Fe-Sin-184#+3:) (:cell align=center:) (:input radio Fe-Sin-184/Fe-Mul-184 B-Fe-Sin-184#+2:) (:cell align=center:) (:input radio Fe-Sin-184/Fe-Mul-184 B-Fe-Sin-184#+1:) (:cell align=center:) (:input radio Fe-Sin-184/Fe-Mul-184 B-Fe-Sin-184#0:) (:cell align=center:) (:input radio Fe-Sin-184/Fe-Mul-184 B-Fe-Sin-184#-1:) (:cell align=center:) (:input radio Fe-Sin-184/Fe-Mul-184 B-Fe-Sin-184#-2:) (:cell align=center:) (:input radio Fe-Sin-184/Fe-Mul-184 B-Fe-Sin-184#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Fe-Mul-184.mp3 width=62 height=18:) (:tableend:)

Second voice conversion

We now going to test the conversion from the same voice A to an other voice B with a french canadian accent. Here you can find example utterances of the two different voices:

The source Voice A :

The target Voice B :

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr bgcolor=#cccc09 align=center:) B (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Ex-20.mp3 width=22 height=18:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Ex-21.mp3 width=22 height=18:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Ex-23.mp3 width=22 height=18:) (:tableend:)

As for the conversion into the first voice speaker, for each of the following file, vote whether it is perceived as closer to the Voice A or to the Voice B.

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr align=center:) File (:cell bgcolor=#cccc99 align=center:) A (:cell bgcolor=#cccc79 align=center:) <- (:cell bgcolor=#cccc59 align=center:) 0 (:cell bgcolor=#cccc29 align=center:) -> (:cell bgcolor=#cccc09 align=center:) B (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-7.mp3 width=62 height=18:) (:cell align=center:) (:input radio Xa-Ex-7c A-Xa-Ex-7c#-2:) (:cell align=center:) (:input radio Xa-Ex-7c A-Xa-Ex-7c#-1:) (:cell align=center:) (:input radio Xa-Ex-7c A-Xa-Ex-7c#0:) (:cell align=center:) (:input radio Xa-Ex-7c A-Xa-Ex-7c#+1:) (:cell align=center:) (:input radio Xa-Ex-7c A-Xa-Ex-7c#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Ex-2.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Ex-2 A-Tr-Ex-2#-2:) (:cell align=center:) (:input radio Tr-Ex-2 A-Tr-Ex-2#-1:) (:cell align=center:) (:input radio Tr-Ex-2 A-Tr-Ex-2#0:) (:cell align=center:) (:input radio Tr-Ex-2 A-Tr-Ex-2#+1:) (:cell align=center:) (:input radio Tr-Ex-2 A-Tr-Ex-2#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-82.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Mul-82 A-Tr-Mul-82#-2:) (:cell align=center:) (:input radio Tr-Mul-82 A-Tr-Mul-82#-1:) (:cell align=center:) (:input radio Tr-Mul-82 A-Tr-Mul-82#0:) (:cell align=center:) (:input radio Tr-Mul-82 A-Tr-Mul-82#+1:) (:cell align=center:) (:input radio Tr-Mul-82 A-Tr-Mul-82#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-71.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Sin-71 A-Tr-Sin-71#-2:) (:cell align=center:) (:input radio Tr-Sin-71 A-Tr-Sin-71#-1:) (:cell align=center:) (:input radio Tr-Sin-71 A-Tr-Sin-71#0:) (:cell align=center:) (:input radio Tr-Sin-71 A-Tr-Sin-71#+1:) (:cell align=center:) (:input radio Tr-Sin-71 A-Tr-Sin-71#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-3.mp3 width=62 height=18:) (:cell align=center:) (:input radio Xa-Ex-3c A-Xa-Ex-3c#-2:) (:cell align=center:) (:input radio Xa-Ex-3c A-Xa-Ex-3c#-1:) (:cell align=center:) (:input radio Xa-Ex-3c A-Xa-Ex-3c#0:) (:cell align=center:) (:input radio Xa-Ex-3c A-Xa-Ex-3c#+1:) (:cell align=center:) (:input radio Xa-Ex-3c A-Xa-Ex-3c#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Ex-6.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Ex-6 A-Tr-Ex-6#-2:) (:cell align=center:) (:input radio Tr-Ex-6 A-Tr-Ex-6#-1:) (:cell align=center:) (:input radio Tr-Ex-6 A-Tr-Ex-6#0:) (:cell align=center:) (:input radio Tr-Ex-6 A-Tr-Ex-6#+1:) (:cell align=center:) (:input radio Tr-Ex-6 A-Tr-Ex-6#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-171.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Mul-171 A-Tr-Mul-171#-2:) (:cell align=center:) (:input radio Tr-Mul-171 A-Tr-Mul-171#-1:) (:cell align=center:) (:input radio Tr-Mul-171 A-Tr-Mul-171#0:) (:cell align=center:) (:input radio Tr-Mul-171 A-Tr-Mul-171#+1:) (:cell align=center:) (:input radio Tr-Mul-171 A-Tr-Mul-171#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-82.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Sin-82 A-Tr-Sin-82#-2:) (:cell align=center:) (:input radio Tr-Sin-82 A-Tr-Sin-82#-1:) (:cell align=center:) (:input radio Tr-Sin-82 A-Tr-Sin-82#0:) (:cell align=center:) (:input radio Tr-Sin-82 A-Tr-Sin-82#+1:) (:cell align=center:) (:input radio Tr-Sin-82 A-Tr-Sin-82#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Xa-Ex-4.mp3 width=62 height=18:) (:cell align=center:) (:input radio Xa-Ex-4c A-Xa-Ex-4c#-2:) (:cell align=center:) (:input radio Xa-Ex-4c A-Xa-Ex-4c#-1:) (:cell align=center:) (:input radio Xa-Ex-4c A-Xa-Ex-4c#0:) (:cell align=center:) (:input radio Xa-Ex-4c A-Xa-Ex-4c#+1:) (:cell align=center:) (:input radio Xa-Ex-4c A-Xa-Ex-4c#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Ex-5.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Ex-5 A-Tr-Ex-5#-2:) (:cell align=center:) (:input radio Tr-Ex-5 A-Tr-Ex-5#-1:) (:cell align=center:) (:input radio Tr-Ex-5 A-Tr-Ex-5#0:) (:cell align=center:) (:input radio Tr-Ex-5 A-Tr-Ex-5#+1:) (:cell align=center:) (:input radio Tr-Ex-5 A-Tr-Ex-5#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-171.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Sin-171 A-Tr-Sin-171#-2:) (:cell align=center:) (:input radio Tr-Sin-171 A-Tr-Sin-171#-1:) (:cell align=center:) (:input radio Tr-Sin-171 A-Tr-Sin-171#0:) (:cell align=center:) (:input radio Tr-Sin-171 A-Tr-Sin-171#+1:) (:cell align=center:) (:input radio Tr-Sin-171 A-Tr-Sin-171#+2:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-71.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Mul-71 A-Tr-Mul-71#-2:) (:cell align=center:) (:input radio Tr-Mul-71 A-Tr-Mul-71#-1:) (:cell align=center:) (:input radio Tr-Mul-71 A-Tr-Mul-71#0:) (:cell align=center:) (:input radio Tr-Mul-71 A-Tr-Mul-71#+1:) (:cell align=center:) (:input radio Tr-Mul-71 A-Tr-Mul-71#+2:) (:tableend:)

Now, as for the first speaker, we ask you to listen to and compare a pair of short utterances and decide which of the two utterances is perceived as more natural by attending to sound quality, i.e., presenting less sound degradation.

1. For each line on the tab, listen carefully to File 1 and File 2.

2. Then give a preference score about according to the following grades tab:

to the left if you prefer file1
to the right if you prefer file2.

(:table border=1 cellpadding=2 cellspacing=0 align=center:) (:cellnr bgcolor=#cccc99 align=center:) File 1 (:cell bgcolor=#cccc99 align=center:) +3 (:cell bgcolor=#cccc89 align=center:) +2 (:cell bgcolor=#cccc79 align=center:) +1 (:cell bgcolor=#cccc59 align=center:) 0 (:cell bgcolor=#cccc39 align=center:) +1 (:cell bgcolor=#cccc19 align=center:) +2 (:cell bgcolor=#cccc09 align=center:) +3 (:cell bgcolor=#cccc09 align=center:) File 2 (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-11.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Sin-11/Tr-Mul-11 B-Tr-Sin-11#+3:) (:cell align=center:) (:input radio Tr-Sin-11/Tr-Mul-11 B-Tr-Sin-11#+2:) (:cell align=center:) (:input radio Tr-Sin-11/Tr-Mul-11 B-Tr-Sin-11#+1:) (:cell align=center:) (:input radio Tr-Sin-11/Tr-Mul-11 B-Tr-Sin-11#0:) (:cell align=center:) (:input radio Tr-Sin-11/Tr-Mul-11 B-Tr-Sin-11#-1:) (:cell align=center:) (:input radio Tr-Sin-11/Tr-Mul-11 B-Tr-Sin-11#-2:) (:cell align=center:) (:input radio Tr-Sin-11/Tr-Mul-11 B-Tr-Sin-11#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-11.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-8.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Sin-8/Tr-Mul-8 B-Tr-Sin-8#+3:) (:cell align=center:) (:input radio Tr-Sin-8/Tr-Mul-8 B-Tr-Sin-8#+2:) (:cell align=center:) (:input radio Tr-Sin-8/Tr-Mul-8 B-Tr-Sin-8#+1:) (:cell align=center:) (:input radio Tr-Sin-8/Tr-Mul-8 B-Tr-Sin-8#0:) (:cell align=center:) (:input radio Tr-Sin-8/Tr-Mul-8 B-Tr-Sin-8#-1:) (:cell align=center:) (:input radio Tr-Sin-8/Tr-Mul-8 B-Tr-Sin-8#-2:) (:cell align=center:) (:input radio Tr-Sin-8/Tr-Mul-8 B-Tr-Sin-8#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-8.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-99.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Mul-99/Tr-Sin-99 B-Tr-Mul-99#+3:) (:cell align=center:) (:input radio Tr-Mul-99/Tr-Sin-99 B-Tr-Mul-99#+2:) (:cell align=center:) (:input radio Tr-Mul-99/Tr-Sin-99 B-Tr-Mul-99#+1:) (:cell align=center:) (:input radio Tr-Mul-99/Tr-Sin-99 B-Tr-Mul-99#0:) (:cell align=center:) (:input radio Tr-Mul-99/Tr-Sin-99 B-Tr-Mul-99#-1:) (:cell align=center:) (:input radio Tr-Mul-99/Tr-Sin-99 B-Tr-Mul-99#-2:) (:cell align=center:) (:input radio Tr-Mul-99/Tr-Sin-99 B-Tr-Mul-99#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-99.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-184.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Sin-184/Tr-Mul-184 B-Tr-Sin-184#+3:) (:cell align=center:) (:input radio Tr-Sin-184/Tr-Mul-184 B-Tr-Sin-184#+2:) (:cell align=center:) (:input radio Tr-Sin-184/Tr-Mul-184 B-Tr-Sin-184#+1:) (:cell align=center:) (:input radio Tr-Sin-184/Tr-Mul-184 B-Tr-Sin-184#0:) (:cell align=center:) (:input radio Tr-Sin-184/Tr-Mul-184 B-Tr-Sin-184#-1:) (:cell align=center:) (:input radio Tr-Sin-184/Tr-Mul-184 B-Tr-Sin-184#-2:) (:cell align=center:) (:input radio Tr-Sin-184/Tr-Mul-184 B-Tr-Sin-184#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-184.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-38.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Sin-38/Tr-Mul-38 B-Tr-Sin-38#+3:) (:cell align=center:) (:input radio Tr-Sin-38/Tr-Mul-38 B-Tr-Sin-38#+2:) (:cell align=center:) (:input radio Tr-Sin-38/Tr-Mul-38 B-Tr-Sin-38#+1:) (:cell align=center:) (:input radio Tr-Sin-38/Tr-Mul-38 B-Tr-Sin-38#0:) (:cell align=center:) (:input radio Tr-Sin-38/Tr-Mul-38 B-Tr-Sin-38#-1:) (:cell align=center:) (:input radio Tr-Sin-38/Tr-Mul-38 B-Tr-Sin-38#-2:) (:cell align=center:) (:input radio Tr-Sin-38/Tr-Mul-38 B-Tr-Sin-38#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-38.mp3 width=62 height=18:) (:cellnr align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Mul-88.mp3 width=62 height=18:) (:cell align=center:) (:input radio Tr-Mul-88/Tr-Sin-88 B-Tr-Mul-88#+3:) (:cell align=center:) (:input radio Tr-Mul-88/Tr-Sin-88 B-Tr-Mul-88#+2:) (:cell align=center:) (:input radio Tr-Mul-88/Tr-Sin-88 B-Tr-Mul-88#+1:) (:cell align=center:) (:input radio Tr-Mul-88/Tr-Sin-88 B-Tr-Mul-88#0:) (:cell align=center:) (:input radio Tr-Mul-88/Tr-Sin-88 B-Tr-Mul-88#-1:) (:cell align=center:) (:input radio Tr-Mul-88/Tr-Sin-88 B-Tr-Mul-88#-2:) (:cell align=center:) (:input radio Tr-Mul-88/Tr-Sin-88 B-Tr-Mul-88#-3:) (:cell align=center:) (:flash http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/dewplayer.swf?son=http://recherche.ircam.fr/equipes/analyse-synthese/lanchant/uploads/Main/test_mp3_IS2010/Tr-Sin-88.mp3 width=62 height=18:) (:tableend:)

A few more questions :

Are you familiar with Speech processing or Voice conversion ? Yes(:input radio expert expert#1:) | No(:input radio expert expert#0:)
Did you use headphones ? Yes(:input radio hp hp#1:) | No(:input radio hp hp#0:)
Your language ? Native french speaker(:input radio French French#2:) | French speaker(:input radio French French#1:) | Other(:input radio French French#0:)

Comments

(:input textarea comments ouch rows=4 cols=60:)

Please, verify that you gave a preference to all questions, then press this button

(:input submit submit "Send the answers !":)

(:input end:)

All recordings are Ircam's property.

Thanks to Gilles Degottex for the php script.

Restore