CAJ | 학술논문

构建一种基于文本和朗读语音共同驱动的双模态语音与口型匹配控制模型，充分利用文本拼音提供正确的口型视位，利用朗读语音为口型视位提供正确的时序，在此基础上对口型几何参数和时间参数进行离散化，根据汉语语音发音机理，合理控制语音的口型动作过程。
구건일충기우문본화랑독어음공동구동적쌍모태어음여구형필배공제모형，충분이용문본병음제공정학적구형시위，이용랑독어음위구형시위제공정학적시서，재차기출상대구형궤하삼수화시간삼수진행리산화，근거한어어음발음궤리，합리공제어음적구형동작과정。
A bimodal-drive matching scheme between Chinese speech and mouth shape is proposed, which is jointly driven by text and read speech. During the disposal of matching, the accurate mouth viseme is calculated with the spelling of text, and the correct time sequence of mouth viseme is given by read speech. Thereafter, the geometrical parameter and the time parameter of mouth motion are discretized. Then, according to the pronunciation mechanism of Chinese speech, the mouth motion of speech is controlled suitably and correctly.