Score and Lyrics-Free Singing Voice Generation

Jen-Yu Liu, Yuhua Chen, Yin-Cheng Yeh, Yi‐Hsuan Yang

arXiv (Cornell University) · 2019 · 16 citations · 31 references

DOIFull text

Open access

Concepts

Abstract

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.

References

31