A Multimodal Positive Computing System for Public Speaking - Evaluating User Responses to Avatar and Video Speaker Representations
Fiona Dermody, Alistair Sutherland · 2018
A multimodal Positive Computing system with real-time feedback for public speaking has been developed. The system uses the Microsoft Kinect to detect voice, body pose, facial expressions and gestures. The system is a real-time system, which gives users feedback on their performance while they are rehearsing a speech. We wish to compare two versions of the system. One version displays a live video-stream of the user. The other displays a computer-generated avatar, which represents the user’s body movements and facial expressions. Visual feedback is displayed on both versions in proximity to the speaking modality it relates to. In all other aspects, the two versions are identical. We found that users rated the video version of the system more distracting as they focussed on their physical appearance rather than their speaking performance when using it