CHAPTER
Evaluation of Multimodal
Interfaces for Ambient
Intelligence
14
Sebastian Mo
¨
ller, Klaus-Peter Engelbrecht, Christine Ku
¨
hnel,
Anja Naumann, Ina Wechsung, and Benjamin Weiss
Quality and Usability Lab, Deutsche Telekom Laboratories, TU Berlin, Berlin, Germany
14.1 Introduction ............................................................................................................ 348
14.2 Performance and Quality Taxonomy.......................................................................... 350
14.3 Quality Factors........................................................................................................ 351
14.4 Interaction Performance Aspects.............................................................................. 352
14.5 Quality Aspects ....................................................................................................... 353
14.6 Application Examples .............................................................................................. 355
14.6.1 INSPIRE and MediaScout ................................................................... 355
14.6.2 Evaluation Constructs ......................................................................... 356
14.6.3 Evaluation of Output Metaphors........................................................... 358
14.6.4 Evaluation of the Quality of an Embodied Conversational Agent ............. 361
14.6.5 Comparison of Questionnaires ............................................................. 363
14.7 Conclusions and Future Work .................................................................................. 367
Acknowledgment.............................................................................................................. 368
References ...................................................................................................................... 368
ABSTRACT
In this chapter, we review assessment and evaluation principles applied to
multimodal interfaces for intelligent environments. On the basis of a new tax-
onomy of quality aspects, quantitative metrics are identified that address differ-
ent aspects of user and system performance, quality, usability, and
acceptability. Example applications are presented for multimodal interfaces to
domestic devices, focusing on information presentation—for example, via an
embodied conversational agent. It is shown which methods are already avail-
able and which ones are still missing to support an efficient development of
ambient intelligence systems that are well accepted by their users.
Key words: multimodal interface, ambient intelligence, evaluation, usability.
© 2010 Elsevier Inc. All rights reserved. 347

Get Human-Centric Interfaces for Ambient Intelligence now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.