EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance.

Yiwei Guo Chenpeng Du Xie Chen Kai Yu

Published in: CoRR (2022)

Keyphrases

text to speech
speech synthesis
prosodic features
text to speech synthesis
word processing
programming tool
image labeling
image intensity
emotional state
english text
human behaviour
general purpose
intensity images
emotion recognition
intensity values
high level
class labels
multi modal
writing skills
pairwise