| Multimodal Modelling |
| Written by Sebastian Feuerstack | |
|
Current Human-Computer Interaction by using the classical desktop-metaphor implemented by a screen, mouse, and keyboard setup requires the complete attention of the user’s eyes as well as his hands. Whereas this type of interaction has been proven to be efficient as it’s the main way of interacting with a computer, in a lot of situations this way is disadvantageous – especially in those situations where you need your hands or eyes for other things, like for instance when driving a car, during cooking, cleaning, playing with your kids and for most other activities in your daily life. Multimodal interaction, by enabling in principle to consider all senses of the human for interaction has two main benefits. On the one hand, it can make interaction more intuitive and easy to learn. On the other hand, it can substitute senses of the user that are currently focused on other actions than interacting with the computer. Or even more important, it can completely substitute a certain way of interaction (e.g. a graphical driven one) by combining other modalities (e.g. speech, gestures and tactile) for (e.g. seeing-) impaired people. Multimodal interaction requires specialized devices to capture and address the human senses, algorithms to calculate the multimodal fusion and fission as well as design processes and frameworks to implement such systems. In my research I am especially interested in prototyping multimodal interaction by the construction of design methods and notations to support the developer and coupling these design models to a runtime environment that can directly interpret the design models to support rapid prototyping and to bridge the gap between what’s designed and what gets implemented. 2008
2007
2006
2005
|
|
| Last Updated ( Sunday, 01 February 2009 ) |