Highly Controllable Diffusion-based Any-to-Any Voice Conversion Model with Frame-level Prosody Feature.

Kyungguen Byun Sunkuk Moon Erik Visser

Published in: CoRR (2023)

Keyphrases

experimental data
mathematical model
high level
prior knowledge
statistical model
formal model
diffusion models
data sets
similarity measure
objective function
probabilistic model
probability distribution
video data
neural network model
diffusion process
diffusion model