Real Time Facial Feature Tracking and Speech Acquisition for Cloned Head Taro Goto, Sumedha Kshirsagar,

In recently developed interactive virtual environments, video and audio are the most fundamental and important as input methods. Video input is used not only for recording and replay, but also for the analysis and recognition of objects and motion. Audio input is an equally intuitive medium for communication with the virtual humans. These media enable an operator to control the environment intuitively without using a special device. For such a situation, we have developed a complete system that covers the aspects from the cloning of a face to its video and audio driven animation. This makes it possible to make a virtual environment rapidly and easily, and act in it through the video and the audio input