Skip to Main Content
This paper describes the progress of our automatic video caption generation project. VC project has developed video caption markup language and its player (VCML and VCML player) to reduce labor and cost of making captions. VCML player, which displays video with its caption, has new functions. One is displaying auditory scene symbol, and another is tree-structured VCML files. Voice-pause method, which was originally developed to align voice intervals and their corresponding written text, has been improved sound data containing both voice and music intervals. The results of the alignment experiment show that the improved method, voice-music-pause method, can align all voice, music and pause intervals effectively.
Multimedia Signal Processing, 2002 IEEE Workshop on
Date of Conference: 9-11 Dec. 2002