The Relationship Between Pauses and Emphasis: Implications for Charismatic Speech Synthesis

Animated voice is engaging, memorable, and entertaining. It is also an important aspect of charismatic behavior. For animated voices, the variations in speed, intensity, and intonation play a role in the perception of charisma. Changes in speed give rise to pauses. And speakers, especially charismatic ones, often use the silence created by pauses to contrast with the emphasis to follow, such as the words spoken with high intensity. How can we realize such behaviors in a virtual character? In this paper, we discuss our work toward the synthesis of charismatic speeches. We collected voice recordings of a tutorial on the human circulatory system in both charismatic and non-charismatic voices using actors from a crowd-sourcing platform. Those recordings were then annotated for occurrence of emphasis. In this paper, we present the analysis of the pauses and emphasis of charismatic and non-charismatic voice recordings, and discuss how they relate to each other and how such findings can inform the synthesis of charismatic speeches for virtual characters.