Audio affect burst synthesis: A multilevel synthesis system for emotional expressions

Affect bursts are short, isolated and non-verbal expressions of affect expressed vocally or facially. In this paper we present an attempt at synthesizing audio affect bursts on several levels of arousal. This work concerns 3 different types of affect bursts: disgust, startle and surprised expressions. Data are first gathered for each of these affect bursts at two different levels of arousal each. Then, each level of each emotion is modeled using Hidden Markov Models. A weighted linear interpolation technique is then used to obtain intermediate levels from these models. The obtained synthesized affect bursts are then evaluated in a perception test.