Audio samples from "DeepConversion:Voice conversion with limited parallel training data"
Authors: Mingyang Zhang, Berrak Sisman, Li Zhao, Haizhou Li
1: Sample 1
Source
Target
DBLSTM
S.M.R
S.E.M.R
W
SI
.M.R
W
SD
.M.R
W
VC
.M.R
W
SI
.E.M.R
W
SD
.E.M.R
W
VC
.E.M.R
2: Sample 2
Source
Target
DBLSTM
S.M.R
S.E.M.R
W
SI
.M.R
W
SD
.M.R
W
VC
.M.R
W
SI
.E.M.R
W
SD
.E.M.R
W
VC
.E.M.R