Modeling error recovery and repair in automatic speech recognition
International Journal of Man-Machine Studies
Providing integrated toolkit-level support for ambiguity in recognition-based interfaces
Proceedings of the SIGCHI conference on Human Factors in Computing Systems
Handheld devices for applications using dynamic multimedia data
Proceedings of the 2nd international conference on Computer graphics and interactive techniques in Australasia and South East Asia
Designing mediation for context-aware applications
ACM Transactions on Computer-Human Interaction (TOCHI)
Hi-index | 0.00 |
The diffusion of mobile devices and the development of their services and applications are connected with the possibility to communicate anytime and anywhere according to a natural approach, which combines different modalities (speech, sketch, etc.) A natural communication approach, such as sketch-based interaction, frequently produces ambiguities Ambiguities can arise in sketch recognition process by the gap between the user's intention and the system interpretation. This paper presents a classification of meaningful ambiguities in sketch-based interaction and discusses methods to solve them taking into account of the spatial and temporal information that characterise the drawing process The proposed solution methods use both sketch-based approaches and/or integrated approaches with other modalities They are classified in: prevention, a-posteriori and approximation methods.