Project: Quality prediction models for conversational interaction in multimodal ...
- Title (NL) Quality prediction models for conversational interaction in multimodal environments
- Period 01 / 2006 - 12 / 2010
- Status Current
- Dissertation Yes
Abstract
Abstract
|
With the growing impact of information technology on daily life, conversational interfaces are becoming increasingly important for providing a natural means of communication between humans and machines. Therefore evaluations and usability tests of such interfaces in order to determine the interface s quality are as crucial as ever. An important question to be answered is what quality means. Although significant progress has been made within the last two decades, there is still no consensus on the definition of quality and its contributing components, as well as on assessment evaluation for such interfaces and prediction methods. This work I address the quality definition problem in context of multimodal conversational interfaces. The work will systematical analyze different multimodal layers (speech, image, text) in order to determine which factors have an influence on the conversational interaction quality. The analysis should also reveal relationships between the factors and their reciprocal influence. Eventually the factors will be integrated into quality prediction model to assess various types of conversational interactions in multimodal environment. |
Related organisations
|
Secretariat
|
Centrum voor Telematica en Informatie Technologie - CTIT (UT) |
|
Financier
|
Europese Commissie |
Related people
|
Supervisor
|
Prof.dr. F.M.G. de Jong |
|
Project leader
|
Dr.ir. H.J.A. op den Akker |
|
Doctoral/PhD student
|
A.I. Niculescu |
Related research (upper level)
Update this data in the Dutch Research Database (NOD).
|
Project
|
Multimedia Semantic Syndication for Enhanced News Services (MESH) |
