Taro Asada¹, Ruka Adachi², Syuhei Takada³, Yasunari Yoshitomi¹, Masayoshi Tabuse^1
1Graduate School of Life and Environmental Sciences, Kyoto Prefectural University, 1-5 Nakaragi-cho, Shimogamo, Sakyo-ku, Kyoto 606-8522, Japan
²Second System Department, Software Service, Inc., 2-6-1 Nishi-Miyahara, Yodogawa-Ku, Osaka, Japan
³Resident Department, Seika Town Hall, 70 Kitashiri, Minamiinayazuma, Nishi-Miyahara, Sagara-Gun, Kyoto, Japan
pp. 60-64
ABSTRACT
Herein, we report on the development of a system for agent facial expression generation that uses vowel recognition when generating synthesized speech. The speech is recognized using the Julius high-performance, two-pass large vocabulary continuous speech recognition decoder software system, after which the agent’s facial expression is synthesized using preset parameters that depend on each vowel. The agent was created using MikuMikuDanceAgent (MMDAgent), which is a freeware animation program that allows users to create and animate movies with agents.

ARTICLE INFO
Article History
Received 14 November 2019
Accepted 20 July 2020

Keywords
MMD Agent
Speech recognition
Vowel recognition
Speech synthesis

JAALR1202

Download article(PDF)