December 6-8, 2010, Sheraton Nashville Downtown, Nashville, TN

Humanoids 2010 Paper Abstract


Paper  MP-II .20

Kraft, Florian (Karlsruhe Institute of Technology (KIT), Germany), Kilgour, Kevin (Karlsruhe Institut of Technologie), Saam, Rainer (Karlsruhe Institute of Technology (KIT), Germany), Stüker, Sebastian (Karlsruhe Institute of Technology (KIT), Germany), Wölfel, Matthias (Universität Karlsruhe (TH)), Asfour, Tamim (Karlsruhe Institute of Technology (KIT)), Waibel, Alex (University of Karlsruhe)

Towards Social Integration of Humanoid Robots by Conversational Concept Learning

Scheduled for presentation during the Interactive "Interactive Session II" ( MP-II ), Monday, December 6, 2010, 15:40−16:40, Ballroom 2/3

2010 IEEE-RAS International Conference on Humanoid Robots, December 6-8, 2010, Sheraton Nashville Downtown, Nashville, TN, USA

This information is tentative and subject to change. Compiled on March 31, 2015

Keywords Human-Humanoid Interaction, Adaptive and Learning Humanoids, Social Robotics (gesture, posture, cognition)


Several real world applications of humanoids in general will require continuous service over a long time period. A humanoid robot operating in different environments over a long period of time means that A) there will be a lot of variation in the speech it has to ground semantically and B) it has to know when a conversation is of interest in order to respond.

Detailed natural speech understanding is hard in real scenarios with arbitrary domains. To prepare the ground for in-domain dialogs in real day-to-day life open domain scenarios we focus on an intermediate attention level based on conversation concept listening and learning.

With the aid of explicit semantic analysis new concepts from open domain conversational speech are learned together with how to react to them according to human needs. This can entail how the robot performs actions such as positioning and privacy filtering.

The corresponding attention model is investigated in terms of concept error rate and word error rate using speech recordings of household conversations.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2015 PaperCept, Inc.
Page generated 2015-03-31  11:00:46 PST  Terms of use