Picture for Cheng-Wei Wu

Cheng-Wei Wu

Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks

Add code
Jul 06, 2018
Cheng-Wei Wu, Jen-Yu Liu, Yi-Hsuan Yang, Jyh-Shing R. Jang
Figure 1 for Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks
Figure 2 for Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks
Figure 3 for Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks

Can we make a famous rap singer like Eminem sing whatever our favorite song? Singing style transfer attempts to make this possible, by replacing the vocal of a song from the source singer to the target singer. This paper presents a method that learns from unpaired data for singing style transfer using generative adversarial networks.

* ICML Workshop 2018 (Joint Music Workshop)  
* 3 pages, 3 figures, demo website: http://mirlab.org/users/haley.wu/cybegan 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon