discoverconferences
SPEAKERS/JEN-YU LIU
Jen-Yu Liu

Jen-Yu Liu

Taiwan AI Labs

Jen-Yu's lectures

lecture cover

Jen-Yu Liu · ICCC'20

Score and Lyrics-Free Singing Voice Generation

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.

lecture cover

Multiple speakers · ICCC'20

Music and Poetry 2