摘要 |
PURPOSE: A method and apparatus of lip-synchronization for voice composition is provided to realize a face of speaking human. CONSTITUTION: The method comprises the steps of: obtaining a code of a phonemes and an information of a syllabic continuance time from a result of voice composition, assigning a phoneme continuance times to a phonemes in the syllabic continuance time, respectively, generating a least one of an animation image key frame indicating a shape of the mouth corresponding to the phoneme refer to a predetermined reference table defined an information of the shape of the mouth, generating the animation image having the shape of the mouth synchronized the result of voice composition, composing the animation image with a still image data, and synchronizing and outputting animation image with the result of voice composition.
|