Details of the submission

Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh, ,,Continuous vocoder in feed-forward deep neural network based speech synthesis'', submitted to DOGS 2017


Samples of the listening test

sentenceNaturalBenchmarkHMM
(Continuous vocoder)
DNN
(WORLD vocoder)
DNN
(Continuous vocoder)
DNN
(Continuous vocoder
+ envelope)
001
002
003
004
005
006
007
008
009
010
011
012
013
014
015