Abstract
The Telecommunications Advancement Organization (TAO) of Japan, has initiated a project in which electronically available text of TV news programs is summarized and synchronized with the speech and video automatically, then superimposed on the original programs for the benefit of the hearing impaired people in Japan. The project started in 1996 and will end in 2001. The main aim of the project is to establish the technology of producing closed caption for TV program efficiently using natural language processing and speech recognition technology. We describe main research issues and show the result of preliminary reseach.
