Speech planning of an anthropomorphic talking robot for consonant sounds production

Kazufumi Nishikawa*, Akihiro Imai, Takayuki Ogawara, Hideaki Takanobu, Takemi Mochida, Atsuo Takanishi

*この研究の対応する著者

研究成果: Conference article査読

12 被引用数 (Scopus)

抄録

This paper describes the speech planning of the anthropomorphic talking robot WT-1R (Waseda Talker-No.1 Refined) for the production of consonant sounds. WT-1R has articulators (the tongue, lips, teeth, nasal cavity and soft palate) and vocal organs (the lungs and vocal cords), and can reproduce human vocal movement. Its total DOF (degrees of freedom) is 15. The vocal movement of WT-1R for vowels is steady. We produced Japanese vowels (/a/, /i/, /u/, /e/, /o/) using the first robot WT-1 in 2000. However, the vocal movement for consonant sounds is transient. We must control the 15-DOF talking robot coordinately in the space and time to reproduce the complicated phenomena of the consonant sounds. Therefore, because the Japanese voice generally consists of two phonemes of the first consonant sound and the last vowel, we proposed the speech planning of WT-1R by considering the phenomenon of the voice as three parts (steady consonant sound, transient consonant sound and vowel). WT-1R could produce Japanese vowels (/a/, /i/, /u/, /e/, /o/) and some consonant sounds (/s/, /h/, /m/, /p/ and /waseda/).

本文言語English
ページ(範囲)1830-1835
ページ数6
ジャーナルProceedings - IEEE International Conference on Robotics and Automation
2
出版ステータスPublished - 2002 1 1
イベント2002 IEEE International Conference on Robotics and Automation - Washington, DC, United States
継続期間: 2002 5 112002 5 15

ASJC Scopus subject areas

  • ソフトウェア
  • 制御およびシステム工学
  • 人工知能
  • 電子工学および電気工学

フィンガープリント

「Speech planning of an anthropomorphic talking robot for consonant sounds production」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル