İkili iletişimler için JESTKOD veri tabanının çok kipli analizi

Gesticulation, together with the speech, is an important part of natural and affective human-human interaction. In human-computer interaction systems, natural, affective and believable use of gestures would be a valuable key component in adopting and emphasizing human-centered aspects. However, natural and affective multimodal data, for studying computational models of gesture and speech, is limited. In this study, the JESTKOD database is introduced, which consists of speech and full-body motion capture data recordings in dyadic interaction setting under agreement and disagreement scenarios. Each participant of the recordings are rated in dimensional affect space. This study includes the evaluations that are performed on the annotations of the database. These evaluations suggest important findings of usability of the JESTKOD database for investigating gesture and speech. Accordingly it is a valuable asset for designing more natural and affective humancomputer interaction systems. Second part of this study also investigates mapping of human body motion observation across different sensor technologies to adapt the JESTKOD database knowledge to other sensors, such as the Kinect.