Synchronization of an animated face with synthetic speech

The creation of audible speech from computer readable text is called text-to-speech (TTS) synthesis. Next-generation TTS systems will have to convert machine-readable text into audible speech using different approach. The aim of research in this field is to increase the naturalness of speech synthesis significantly while maintaining good intelligibility. Synthetic realistic mouth motions matching the speech sounds not only give the perception that the image is talking, but can actually increase the intelligibility of the speech (increased redundancy). Also, there is a psychological moment: animated images (agents, avatars, virtual personae) can increase a user's patience while waiting on searches and database retrievals. The newest advance in the visual TTS (VTTS) is given.