ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Text-driven Speech Animation with Emotional Expressions
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Wonseok Chae, Jungjin Park, Soo-Myung Pahk, Hyung-Keun Jee, Yejin Kim
Issue Date
2019-12
Citation
International Conference on Internet (ICONI) 2019, pp.204-206
Language
English
Type
Conference Paper
Abstract
In this paper, we propose a novel approach to create a speech animation with emotional expressions using a small set of example models. To generate realistic facial animation, two example models called key visemes and expressions are used for lip-synchronization and facial expressions, respectively. Based on a phonetic transcript generated by a text-to-speech (TTS) system, a sequence of facial animation is synthesized by blending the corresponding sequence of key example models. The proposed approach can be applied to diverse digital contents and applications that use facial animation.
KSP Keywords
Digital content, Emotional expression, Facial animation, Facial expression, Novel approach, Small set, Speech animation, Text-To-Speech(TTS)