Paper

Distilling Sequence-to-Sequence Voice Conversion Models For Streaming Conversion Applications

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Shogo Seki

Audio samples

Cross gender: fym (female) --> msh (male)
(Supported: Safari, Chrome, FireFox, Opera)

Re-synthsized			Proposed
Source	Target	Baseline	Approach-1	Approach-2	Approach-3	Approach-4

Intra gender: fym (female) --> ftk (female)

Intra gender: mht (male) --> msh (male)

Cross gender: mht (male) --> ftk (female)