|
EXHIBITION
In Tokuda & Lee laboratory, softwares for promotion of speech and image research are developed and opened to the public. These are used to research in various organizations and companies.
Software
HMM Speech Sysnthesis System toolkit: HTS
#ref(): File not found: "01.jpg" at page "ホーム/公開物"
HTS is a basic software for speech synthesis that a lot of research laboratories(Microsoft, IBM, etc) adopt.
General-purpose large vocabulary continuous speech recognition decoder: Julius
#ref(): File not found: "02.jpg" at page "ホーム/公開物"
This is a speech recognition software that is adopted by various research laboratories, and maintains Google Rank of the top of Japan as free software.
Speech signal processing toolkit: SPTK
#ref(): File not found: "03.jpg" at page "ホーム/公開物"
This is a software that does signal processing and data processing for the acoustical analysis.
Anthropomorphic spoken dialogue agent: Galatea
#ref(): File not found: "04.jpg" at page "ホーム/公開物"
This is an open-source, license-free software toolkit for building anthropomorphic spoken dialogue agents. This is a product of project which speech, language, and image researchers from ten or more university in Japan participate to build anthropomorphic spoken dialogue agents. HTS and Julius, those are developed in this laboratory, are used on speech wave form generation module and speech recognition module respectively in this software.
Data base
Multimodal speech data base for research: M2TINIT
#ref(): File not found: "05.jpg" at page "ホーム/公開物"
Kobayashi Takao laboratory *1
Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
マルチモーダル音声研究の推進のため，東京工業大学大学院院総合理工学研究科 小林隆夫研究室，および名古屋工業大学知能情報システム学科 北村・徳田研究室(現在，情報工学科 徳田・李研究室)が開発・公開する音声・唇動画像同時収録データベースです．
これまでに音声・唇動画像の生成やバイモーダル音声認識の研究に利用されています．
