"Parallel-data-free Emotional Voice Conversion with CycleGAN and Continuous Wavelet Transform",
Authors: Kun Zhou, Berrak Sisman, Haizhou Li
submitted to Odyssey 2020
Examples of synthesized speech by "Baseline" , "Joint Training" and "Separate Training" systems.
Baseline: Conventional CyleGAN-based VC framework with LG normalized F0 transformation
Joint Training: Joint training CycleGAN-based emotional VC framework with CWT-F0 transformation
Separate Training: Separate training CycleGAN-based emotional VC framework with CWT-F0 transformation