Text-driven Visual Prosody Generation for Embodied Conversational Agents.

Jiali Chen Yong Liu Zhimeng Zhang Changjie Fan Yu Ding

Published in: IVA (2019)

Keyphrases

embodied conversational agents
text to speech
text generation
text mining
information retrieval
virtual characters
visual information
news video
speech synthesis
audio visual
web images
synthesized speech
keywords
visual features
language learning