A new Testbed for Semi-Automatic Usability Evaluation and Optimization of Spoken Dialogue Systems
Spoken dialogue platforms usually log a multitude of information for each interaction between user and system. Such information is potentially very helpful for system evaluation and optimization; however, it is very difficult to interpret log data due to
- PDF / 434,756 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 4 Downloads / 197 Views
Sebastian Möller and his renowned project partners take things a step further: How can automatically obtained user information be exploited in a tool that helps optimize future speech dialog systems by considering as much information as possible from a user perspective? Users’ assessments from real usability tests were taken and compared with data collected in the system’s log files.
Prof. Dr.-Ing. Sebastian Möller Sebastian Möller is Professor for Usability at the Quality and Usability Lab, Deutsche Telekom Laboratories, Berlin Institute of Technology, Germany. He received his PhD (Dr.-Ing.) from Ruhr-Universität Bochum in 1999 for his work on the assessment and prediction of speech quality in telecommunications, and got the qualification to be a professor (venia legendi) at that university in 2004, with a book on the quality of telephonebased spoken dialogue systems. His main research interests are on speech processing, speech technology, communication acoustics, quality assessment, and on the usability of telecommunication services. Since 1997, he has taken part in the standardization activities of the International Telecommunication Union (ITU-T).
Klaus-Peter Engelbrecht Klaus-Peter Engelbrecht is working as a research assistant at the Quality and Usability Lab of Deutsche Telekom Laboratories (T-Labs), TU-Berlin. He studied Communication Research and Musicology and received his Magister degree in 2006 from Berlin Institute of Technology. At T-Labs, he is working towards his PhD thesis in the domain of automated usability evaluation for spoken dialog systems.
Dr. Michael Pucher Michael Pucher studied philosophy at the University of Vienna and computational logic at Vienna University of Technology. Since 2001 he is working at the Telecommunications Research Center Vienna (ftw.) where he is currently senior researcher and project manager. In 2007 he received a doctoral degree in Electrical Engineering from Graz University of Technology. He was a visiting researcher at the International Computer Science Institute in Berkeley (ICSI) and at Deutsche Telekom Laboratories in Berlin (T-Labs). His research interests are speech synthesis, language modeling for speech recognition, and multimodal and spoken dialog systems. Currently he is working on Viennese sociolect and dialect speech synthesis for regionalized voice services.
Dr. Peter Fröhlich Peter Fröhlich studied Psychology at University of Salzburg and music education at Mozarteum Salzburg. In 2007, he received a doctoral degree in Applied Psychology from University of Vienna. From 2000 to 2003, Peter worked as usability specialist at CURE – Center for Usability Engineering and Research in Vienna. Since December 2003, he joined Telecommunications Research Center Vienna (ftw.) as a Senior Researcher responsible for the Human-TelecomSystems Interaction Lab. Peter is also lecturer for Usability at FHWien University of Applied Sciences. His research interests include auditory and multimodal HCI, research methodology, mobile spatial interaction, eLearning, and inte
Data Loading...
