Skip to main content

Research Talk:  SocioPhone - Mobile interaction sensing system and its applications

Date:May 1, 2014 
Talk Title:SocioPhone - Mobile interaction sensing system and its applications
Speaker:Youngki Lee, Assistant Professor, Singapore Management University
Time & Location:12:00pm - 1:00pm
CIC Building, Pittsburgh


Face-to-face interaction, especially conversation, is a fundamental part of everyday life. In mobile and pervasive computing domain, face-to-face interaction is often simply abstracted as a contact in proximity; however, to design more useful applications for interaction situations, much deeper contextual understanding is required. In this talk, I will first introduce SocioPhone, a mobile system for face-to-face interaction monitoring. In its core, SocioPhone monitors conversational turns, a continuous speech segment where a person starts and ends her speech. We have noticed that monitoring turns is a first crucial step to deriving many interesting aspects of a conversion, e.g., how long and often one talks, how quickly she responds, who talks more or less, and how fast a conversation progresses. More interestingly, turn analysis enables high-level social inference, such as one’s role in a conversation and problematic situations. SocioPhone abstracts such useful turn-driven conversational contexts as a set of intuitive APIs. Its runtime efficiently monitors registered contexts during in-progress conversations and notifies applications on-the-fly. Then, I will introduce a novel Sociophone application, TalkBetter, in more detail. TalkBetter is a mobile in-situ intervention service for everyday clinical care for children with language delay, which is firmly grounded on extensive collaboration with speech-language pathologists. I will present the design process and initial evaluation of TalkBetter, and discuss further opportunities regarding language-related disorders. 

Speaker Bio

Youngki Lee is an assistant professor of School of Information Systems at Singapore Management University. He received his Ph.D  in computer science at KAIST, Korea. He has broad interests in building creative and experimental software systems and futuristic applications, which requires deep understanding on computer systems, applications, and users. More specifically, he has been building mobile and sensor systems to enable always-available and highly-enriched context awareness and addressed core technical issues such as energy efficiency, resource coordination, and recognition accuracy. On top of his platform, he also built a number of useful life-immersive sensing applications in diverse application domains, for example, childcare, healthcare, advertisements, gaming. He published his work in premier conferences and journals such as ACM MobiSys, ACM SenSys, ACM CSCW, IEEE PerCom, Pervasive, Communications of ACM, and IEEE TMC. For more details, visit