ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition
April 13-16, 2003
The identificaion of basic units in spontaneous Japanese is an indispensable issue for spokan language processing. This paper describes a method for the semi-automatic detection of "sentences" from the Corpus of Spontaneous Japanese (CSJ).
Bibliographic reference. Takanashi, Katsuya / Maruyama, Takehiko / Uchimoto, Kiyotaka / Isahara, Hitoshi (2003): "Identification of "sentences" in spontaneous Japanese - Detection and modification of clause boundaries", in SSPR-2003, paper TAP4.