This paper describes a Chinese text-to-visual speech synthesis system based on data-driven (sample based) approach, which is realized by short video segments concatenation.
给出一个基于数据驱动方法(基于样本方法)的汉语文本-可视语音合成系统，通过将小段视频拼接生成新的可视语音。
Lip is one of the most important facial features, and plays key roles in a variety of fields such as audio-visual speech, authentication, lip synchronization, face recognition, etc.
嘴唇是人脸特征的重要组成部分，在音视频识别、认证、嘴唇同步、人脸识别等方面都很重要。
Lip is one of the most important facial features, and plays key roles in a variety of fields such as audio-visual speech, authentication, lip synchronization, face recognition, etc.
嘴唇是人脸特征的重要组成部分，在音视频识别、认证、嘴唇同步、人脸识别等方面都很重要。
应用推荐