English

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

Sound 2018-07-09 v1 Artificial Intelligence Audio and Speech Processing

Abstract

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.

Cite

@article{arxiv.1807.02254,
  title  = {Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks},
  author = {Cheng-Wei Wu and Jen-Yu Liu and Yi-Hsuan Yang and Jyh-Shing R. Jang},
  journal= {arXiv preprint arXiv:1807.02254},
  year   = {2018}
}

Comments

3 pages, 3 figures, demo website: http://mirlab.org/users/haley.wu/cybegan

R2 v1 2026-06-23T02:52:33.929Z