Logo: University of Southern California

Events Calendar


  • CS Colloquium - Stefan Scherer (ICT): Computational Behavior Analytics for Healthcare Applications

    Thu, Jan 30, 2014 @ 04:00 PM - 05:30 PM

    Thomas Lord Department of Computer Science

    Conferences, Lectures, & Seminars


    Speaker: Stefan Scherer, USC Institute for Creative Technologies [ICT]

    Talk Title: Computational Behavior Analytics for Healthcare Applications

    Series: CS Colloquium

    Abstract: Computational Behavior Analytics aims to automatically identify, characterize, model, and synthesize individuals' multimodal nonverbal behavior within both human-machine as well as machine-mediated human-human interaction. The emerging technology of this field of research is relevant for a wide range of interaction applications, including the areas of healthcare and education. Exemplarily, the characterization and association of nonverbal behavior with underlying clinical conditions, such as depression or post-traumatic stress disorder (PTSD), holds transformative potential and could change treatment and help improve the healthcare systems' efficiency significantly. Within this talk I will present our recent findings of automatically assessed multimodal nonverbal behaviors indicative of depression and PTSD. In particular, we can confirm and enrich present state of the art, predominantly based on qualitative and tedious manual annotations, with automatic quantitative behavior descriptors that can assist doctors in making more informed decisions. Within this context, I will focus my talk on the characterization of a speaker's voice, utilizing both prosodic and voice quality estimates. I will discuss the integration of perceptual salience in both novel multimodal machine learning algorithms, which can leverage uncertainty in the target classes, and alternative feature extraction mechanisms, that reflect human characteristics of production and perception. To conclude the talk I will highlight complementary application areas that illustrate the integration and versatility of the presented speech technology for automatic behavior synthesis and computer assisted learning.

    Biography: Stefan Scherer was born on the 28th of February 1983 in Feldkirch Austria. In July 2011, he finished his doctoral studies to receive the degree of Dr. rer. nat. from the faculty of Engineering and Computer Science at Ulm University. Scherer’s thesis, entitled “Analyzing the User’s State in HCI: From Crisp Emotions to Conversational Dispositions”, received the grade summa cum laude (i.e. with distinction). During his time as a PhD student, Scherer had the opportunity to co-supervise thesis projects of several international students, co-organize lectures and seminars, participate in the graduate school of the SFB/TRR 62 (a German Research Foundation funded project), act as the speaker of the PhD students, and work at the Advanced Telecommunications Research Institute (ATR) in Kyoto Japan in collaboration with Prof. Nick Campbell as a visiting researcher supported by the German Exchange Service (DAAD). As a postdoctoral researcher, he had the opportunity to collect experience at the internationally renowned Trinity College Dublin in Ireland. Currently, Scherer is working as Postdoctoral Research Fellow at the University of Southern California Institute for Creative Technologies under the supervision of Louis-Philippe Morency. His research fields of interest are human machine interaction, social signal processing, and affective computing.

    Host: Aiichiro Nakano

    Location: Henry Salvatori Computer Science Center (SAL) - 101

    Audiences: Everyone Is Invited

    Contact: Assistant to CS chair

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File

Return to Calendar