Score and Lyrics-Free Singing Voice Generation

Understand

Generative models for singing voice have been mostly concerned with the task of ``singing voice synthesis,'' i.e., to produce singing voice waveforms given musical scores and text lyrics.

• In this work, we explore a novel yet challenging alternative: singing voice generation without pre-assigned scores and lyrics, in both training and inference time.
• In particular, we outline three such generation schemes, and propose a pipeline to tackle these new tasks.
• Moreover, we implement such models using generative adversarial networks and evaluate them both objectively and subjectively.