CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion

9 Apr 2019 • Takuhiro Kaneko • Hirokazu Kameoka • Kou Tanaka • Nobukatsu Hojo

Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been challenging due to the disadvantages of the training conditions... (read more)

PDF Abstract

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Residual Connection	Skip Connections
Batch Normalization	Normalization
GAN Least Squares Loss	Loss Functions
Cycle Consistency Loss	Loss Functions
ReLU	Activation Functions
Sigmoid Activation	Activation Functions
Tanh Activation	Activation Functions
Leaky ReLU	Activation Functions
Residual Block	Skip Connection Blocks
Convolution	Convolutions
Instance Normalization	Normalization
PatchGAN	Discriminators
CycleGAN	Generative Models

METHOD

TYPE

Residual Connection