TRANSLINGUAL COMBINATION OF VISUAL VOICE

摘要

PROBLEM TO BE SOLVED: To provide a computer packaging method in which audio driving type face animation is generated employing a voice recognition system for only one language in a system that is independent of language. SOLUTION: The method is based on the recognition in which mapping and animation are practically independent of language after matching is generated. When a first step of matching generation is made independent of voice, translingual combining of visual voice is achieved. In this method, the video is combined with any new language voice to be inputted if a voice recognition system for a base language exists.