SFSA (Synchronized facial speech animator)

• Main Authors: Acuna, Willeus K., Fabros, Ronaldo R., Koh, Monette O., Saturnino, Alma Theresa A.
• Format: text
• Language: English
• Published: Animo Repository 1995
• Subjects: Animation; Windows (Computer programs); Face perception; Speech processing systems; Computer graphics; Human-computer interaction
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/5909
• Institution: De La Salle University

The Synchronized Facial Speech Animator (SFSA) is a Windows-based system that models human facial expressions in synchrony with speech. Animation is controlled by specifying contraction values for each individual muscle over several time periods. The muscles are grouped into several regions namely the left forehead, the right forehead, the left eye, the right eye, the nose, the left cheek, the right cheek, and the mouth. Each of these regions could be animated separately from the others. Speech is generated from any input text with the use of a phoneme-based dictionary. The dictionary contains over 12,000 lexicon entries from which any English utterance can be pronounced. Lexicon entries can be added to or can be deleted from the existing dictionary. Animation is made using a single face and a single voice. Head rotation, ear movements, tongue articulation, and hair perturbations are excluded from the animation. The generated speech is perceived as being artificial, monotonous, slow, but intelligible. The animated lip movements are perceived to be synchronized with the appropriate sounds.