2022
KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE Using Mel-Spectrograms
ICASSP 2022accepted
In this paper, we propose a novel neural network model called KaraSinger for a less-studied singing voice synthesis (SVS) task named score-free SVS, in which the prosody and melody are spontaneously decided by machine. KaraSinger comprises a vector-quantized variational autoencoder (VQ-VAE) that com…