VOICE-BASED AUTOMATIC LIP-SYNCHRONIZATION ANIMATION APPARATUS, VOICE-BASED AUTOMATIC LIP-SYNCHRONIZATION ANIMATION METHOD, AND STORAGE MEDIUM

摘要

The present invention relates to a voice-enabled automated lip sync animation apparatus and method and a recording medium, receiving a voice file and a text file that contains all the voice information of the voice file containing the pronunciation of the metabolic, each pronunciation in the voice file after the separation by the content-specific syllable pronunciation time information and the extracted phoneme pronunciation for outputting the result as a file in the text file information generator; Lip to the pronunciation information distinguish the information in the file from the generator by syllable / phoneme based on the default pronunciation model to extract the position the position of the key frame for the animation, and branding the extracted location-specific key frame to the natural lip synch animation keyframe regulator; The lip-sync lip-sync animation previewer for using keyframes from the keyframe regulator generates a lipsync animation information in every frame, and the main display real-time lip-sync animation on the screen with the information of all the lip-sync animation frames that generation; And which are for voice recognition and a number of phoneme models predefined lip stores a plurality of basic pronunciation models and Hangul number of branding rules model to a defined syllables as the basis used for the animation, the pronunciation information generator and lip-sync key by the regulator frame and lip-sync animation previewer and a sound model database that is within the data are read out.