Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks
arXiv:1807.02254v110 citations
Originality Synthesis-oriented
AI Analysis
This addresses the challenge of modifying vocal styles in music for applications like entertainment or content creation, but appears incremental as it builds on existing GAN techniques.
The paper tackles the problem of singing style transfer, enabling a target singer to perform a source song using unpaired data, and achieves this through a method based on 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.