Software that can automatically recognize “non-linguistic” sounds such as laughter and generate an appropriate facial animation sequence, could improve the quality of web-based avatars or computer-animated movies.

University of Bath and University of Cardiff scientists used optical motion capture to record the facial expressions of four participants as they performed a number of laughs, sobs, sneezes and yawns. The researchers also recorded the participants’ voices during their performances. They then developed software that correlates the key audio features of each non-linguistic vocalization with the relevant facial motion-capture data.