[BIN]: Facial animation with text-to-speech synthesizer

• Main Authors: Diaz, Catherine R., Gayao, Grace P., Perez, Rolando M., Jr., Polican, Marc Anthony T.
• Format: text
• Language: English
• Published: Animo Repository 2002
• Subjects: Computer animation; Facial expression in art; Computer-aided design; Computer simulation; Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/14249
• Institution: De La Salle University

[Bin] is a system that incorporates facial animation with a text-to-speech synthesizer. It accepts an input string together with some simulation controls such as speech rate and facial expressions. Using these input parameters, [Bin] will produce a series of three-dimensional facial snapshots that is synchronized with the audio stream generated by the text-to-speech synthesizer. The facial model speaks the input string and produces a synchronized facial animation. The predefined set of facial expressions includes anger, happiness, fear, disgust, surprise, and sadness. The system can be primarily used in the field of education, computer games, cartoons, telecommunication services and broadcasting.