Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation.

Rohan Chaudhury Mihir Godbole Aakash Garg Jinsil Hwaryoung Seo

Published in: CoRR (2024)

Keyphrases

speech synthesis
speech recognition
text to speech
vocal tract
prosodic features
facial expressions
speech corpus
real time
text to speech synthesis
database
machine learning
bayesian networks
generation process
emotion recognition