Facial Expression Synthesis Using Vowel Recognition for Synthesized Speech

被引：0

作者：

Asada, Taro ^{[1
]}

Adachi, Ruka ^{[2
]}

Takada, Syuhei ^{[3
]}

Yoshitomi, Yasunari ^{[1
]}

Tabuse, Masayoshi ^{[1
]}

机构：

[1] Kyoto Prefectural Univ, Grad Sch Life & Environm Sci, Sakyo Ku, 1-5 Nakaragi Cho, Kyoto 6068522, Japan

[2] Software Serv Inc, Yodogawa Ku, 2-6-1 Nishi Miyahara, Osaka, Japan

[3] Seika Town Hall,70 Kitashiri, Kyoto, Japan

来源：

PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON ARTIFICIAL LIFE AND ROBOTICS (ICAROB2020) | 2020年

关键词：

MMDAgent; Speech recognition; Vowel recognition; Speech synthesis;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：398 / 401

页数：4