Human-Centered Computing: Using Speech to Understand Behavior

Emotion and mood have intrigued researchers for generations. This fascination has permeated the engineering community, motivating the development of affective computational models for classification, particularly in the domain of assistive technology for mental health. Effective treatment and monitoring for individuals with mental health disorders is an enduring societal challenge. Regular monitoring increases access to preventative treatment, but is often cost prohibitive or infeasible given high demands placed on health care providers. Yet, it is critical for individuals with Bipolar Disorder (BPD), a chronic psychiatric illness characterized by mood transitions between healthy and pathological states. Transitions into pathological states are associated with profound disruptions in personal,social, vocational functioning,and emotion regulation . I will present our ongoing work investigating new approaches in speech-based mood and emotion modeling.
Emily Mower Provost is an Assistant Professor in the Computer Science and Engineering Department (CSE) at the University of Michigan. She received her B.S. degree in electrical engineering from Tufts University, Boston,MA, in 2004 and her M.S. and PhD degrees in electrical engineeringfrom the University of Southern California (USC), Los Angeles, in 2007 and 2010, respectively. Her research interests are in human-centered speech and video processing and multimodal interfaces design. The goals of her research are motivated by the complexities of human emotion generation and perception. She seeks to provide a computational account of how humans perceive emotional utterances ("emotion perception" ) and combines this with knowledge gleaned from perception estimation studies
("emotion recognition" ) to develop systems capable of interpreting naturalistic expressions of emotion utilizing a new quantification measure ("emotion profiles" ). She has published many articles in these areas and is a contributor to the winning paper in the classifier category of the 2009 lnterspeech Emotion Challenge, a best student paper at ACM Multimedia 2014, and an honorable mention at IEEE ICMI 2016. She also received the Oscar Stern Award for Depression Research (2015).