S
Shin-ichi Kawamoto
Researcher at National Institute of Information and Communications Technology
Publications - 17
Citations - 79
Shin-ichi Kawamoto is an academic researcher from National Institute of Information and Communications Technology. The author has contributed to research in topics: Animation & Speaker recognition. The author has an hindex of 5, co-authored 17 publications receiving 75 citations.
Papers
More filters
Book ChapterDOI
Galatea: Open-Source Software for Developing Anthropomorphic Spoken Dialog Agents
Shin-ichi Kawamoto,Hiroshi Shimodaira,Tsuneo Nitta,Takuya Nishimoto,Satoshi Nakamura,Katsunobu Itou,Shigeo Morishima,Tatsuo Yotsukura,Atsuhiko Kai,Akinobu Lee,Yoichi Yamashita,Takao Kobayashi,Keiichi Tokuda,Keikichi Hirose,Nobuaki Minematsu,Atsushi Yamada,Yasuharu Den,Takehito Utsuro,Shigeki Sagayama +18 more
TL;DR: Galatea as mentioned in this paper is a software toolkit to develop a human-like spoken dialog agent, which integrates the modules of different characteristics including speech recognizer, speech synthesizer, facial animation synthesizer and dialog controller.
Book ChapterDOI
Analysis on Effects of Text-to-Speech and Avatar Agent in Evoking Users’ Spontaneous Listener’s Reactions
Teruhisa Misu,Etsuo Mizukami,Yoshinori Shiga,Shin-ichi Kawamoto,Hisashi Kawai,Satoshi Nakamura +5 more
TL;DR: An HMMbased dialogue-style TTS system that generates human-like cues that evoke users’ backchannels and an avatar agent that can make several listener’s reactions is constructed that is evaluated in terms of evoked user backch channels.
Proceedings ArticleDOI
Perceptual similarity measurement of speech by combination of acoustic features
TL;DR: This paper investigates acoustic features to estimate perceptual similarity of speech individuality and proposes a method linearly combined eight acoustic features related to the perception of speech individualities that optimizes weights for the acoustic features considering perceptual similarities.
Proceedings Article
Toward Construction of Spoken Dialogue System that Evokes Users' Spontaneous Backchannels
Teruhisa Misu,Etsuo Mizukami,Yoshinori Shiga,Shin-ichi Kawamoto,Hisashi Kawai,Satoshi Nakamura +5 more
TL;DR: An HMM-based dialogue-style text-to-speech (TTS) system that generates human-like cues that evoke users' backchannels is constructed that is more informative for the system in detecting users' feelings than those by conventional reading-style TTS.
Proceedings ArticleDOI
Data-driven efficient production of cartoon character animation
Shigeo Morishima,Shigeru Kuriyama,Shin-ichi Kawamoto,Tadamichi Suzuki,Masaaki Taira,Tatsuo Yotsukura,Satoshi Nakamura +6 more
TL;DR: It seems that the two technologies, MoCaToon and AniFace, can be effectively used by animators to customize 3DCG characters according to their specific requirements, especially in terms of character style and motion.