A CSC Guest Presentation: Automatic Emotion Recognition: Developing Machines that Identify Human Emotion Presentation by: Yelin Kim, PhD Candidate, University of Michigan, Electrical Engineering and Computer Science Thursday, October 15 at 7PM Conference Room 4, Michigan League Can machines identify human emotion? My main research interest is the automatic analysis of human behavior during real-world interactions between human-human and human-machine. In particular my PhD work focuses on developing systems for automatic sensing, quantification, and interpretation of an individual’s emotion based on their face and voice during dyadic (two-person) interaction. Any human-human or human-machine interactions evoke and involve affective and social signals, such as emotion, social attitude, engagement, conflict, and persuasion. These signals can be inferred from both verbal and nonverbal human behavior, such as words, head and body movements, facial expressions, tone of voice, eye gaze, and turn taking. The signals profoundly influence the overall outcome of interactions, and hence the understanding of these signals will enable us to build human-centered interactive technology tailored to an individual user’s needs, preferences, and capabilities.