Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training.

Jan Melechovský Ambuj Mehrish Berrak Sisman Dorien Herremans

Published in: CoRR (2024)

Keyphrases

text to speech
speech synthesis
prosodic features
programming tool
speech recognition
multi agent
supervised learning
spoken language
machine learning
training phase
multi layer
online learning
training set
training samples
pattern recognition
data sets
writing skills
text to speech synthesis