#mintlab

This Friday, we’re starting with a new concept at the Meaningful Interactions Lab (KU Leuven - imec), the research group where I’ve working for more than 4 years now. Every few weeks we will invite speakers from academia or industry, active in Human-Computer Interaction or related fields, to give a talk about their research.

For the 1st edition of our Basement Talks, we’re welcoming Cristina Zaga and Prof. Khiet Truong from UTwente who will talk about their exciting work in Child-Robot Interaction. If you’re in or around Leuven on the 10th of February (1:00 - 2:00 pm), feel free to drop by! The presentations take place in Mintlab’s Designroom in... the basement.

Please confirm your attendance via email to maarten.vanmechelen[at]kuleuven.be

Khiet Truong is an assistant professor in the Human Media Interaction group, University of Twente. Her interests lie in the automatic analysis and understanding of verbal and nonverbal (vocal) behaviours in human-human and human-machine interaction, and the design of socially interactive technology to support human needs. Taking an interdisciplinary approach within the realms of affective computing and social signal processing, she aims to develop socially and affective intelligent interfaces (e.g. virtual conversational agents, social robots) that can recognize and display social and affective signals, and she aims to study how humans interact with this new kind of technology. Coming from a background in (computational) paralinguistics and speech analysis, her main focus is on analysing the vocal modality of expression, in addition to the visual (e.g. facial expressions, eye gaze) and physiological (e.g. heart rate, galvanic skin response) modalities in social interaction.

In her talk, Khiet will discuss what kinds of non-verbal behaviors (mainly in speech communication) can be important in human-machine interaction. How can we model these non-verbal behaviors for affective and socially interactive technology? Khiet will present some results of her studies on the analysis of non-verbal behavior in speech.

Khiet has a master in Computational Linguistics (Utrecht University). For her master research, she was with Radboud University Nijmegen investigating automatic pronunciation error detection in L2-speech. In her PhD research carried out at TNO, Khiet investigated emotion recognition in speech and automatic laughter detection.

Cristina Zaga is a PhD candidate in the Human Media Interaction group (University of Twente) and she works on the EU FP7 Project Squirrel (Clearing Clutter Bit by Bit). Her research revolves around child-robot interaction at the intersection of interaction design, robotics and social science. Cristina studies how minimal nonverbal behaviour — minimal motion coupled with semantic free utterances —  supplies non-anthropomorphic robots with the communicative power necessary to engage as ‘cooperative peers’ in playful tasks with children (8-10 years old). Specifically, she investigates (i) how minimal nonverbal behaviour legibly communicates robot’s support in tasks (ii) whether children ascribe animacy and pro-social qualities to the robot behaviour; and (iii) whether the robot behaviour shapes children’s cooperative dynamics in the task. Her design process strives to complement human-robot interaction design methodologies with generative techniques. To this end, she is exploring methods to externalize children’s perception and ideas on robot’s behaviour through kinaesthetic activities and design improvisations sessions.

In her talk, Cristina will present preliminary results that show potential benefits of coupling movements with a type of semantic free utterances (i.e., gibberish speech) to positively affect cooperative task performance and shape children’s cooperation in playful tasks. She will discuss design methodologies and research implications for human-robot interaction and interaction design.