Variational Autoencoding Wasserstein GAN

Spectral Voice Conversion using VAW-GAN

Our Teams View on GitHub

Welcome to Voice Conversion Demo.

This is the demonstration of our experimental results in Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks, where we tried to improve the conversion model by introducing the Wasserstein objective.

SF1
SF1
TF2
Change target

Source

Target

VAE (baseline)

VAW-GAN

Source

Target

VAE (baseline)

VAW-GAN

Source

Target

VAE (baseline)

VAW-GAN