Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Toward the Realization of Spontaneous Speech Recognition - Introduction of A Japanese Priority Program and Preliminary Results -

Sadaoki Furui (1,2), Kikuo Maekawa (2), Hitoshi Isahara (3), Takahiro Shinozaki (1) and Takashi Ohdaira (1)

(1) Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan
(2) The National Language Research Institute, Kita-ku, Tokyo, Japan
(3) Communications Research Laboratory, Nishi-ku, Kobe, Japan

Although high-recognition accuracy can be obtained for speech in the form of reading a written text or similar by using state-ofthe art speech recognition technology, the accuracy is quite poor for freely spoken spontaneous speech. From this perspective, a new national project for raising the technological level of speech recognition and understanding has recently commenced in Japan. This paper first briefly introduces the project and then reports some results of preliminary experiments which have been conducted at Tokyo Institute of Technology.

Full Paper

Bibliographic reference.  Furui, Sadaoki / Maekawa, Kikuo / Isahara, Hitoshi / Ohdaira, Takahiro Shinozaki (1) and Takashi (2000): "Toward the realization of spontaneous speech recognition - introduction of a Japanese priority program and preliminary results -", In ICSLP-2000, vol.3, 518-521.