We have been handling video with supplementary documents, such as cooking programs, and are working on integration of such media. Through the integration, many applications will become possible, for example, reconstruction of multimedia data that supplement the information of each medium, construction of interactive database, or kitchen automation. Until now, we have proposed an integration system that perform integrative analysis of image, audio and text and associate each other. In this paper, we will introduce the latest text analysis result and discuss about future image and audio analysis of the proposed system.