Multimodal interfaces for multimedia information agents

MaRDI QIDQ4942764zbMATH OpenFDO

Authors Alex Waibel, Bernhard Suhm, Minh Tue Vo, Jie Yang

Publication date 5 June 2000

zbMATH Keywords

multimodal interfacesQuickDoc

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Knowledge representation (68T30) Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence (68T35) Natural language processing (68T50)

Review text

This paper describes information agents that use multimodal interfaces to access, manipulate, create and disseminate information. The authors show that the addition of non-acoustic or non-verbal cues can significantly enhance robustness, flexibility, naturalness and performance of human-computer interaction. Effective methods and cross-modal cues arc discussed aiming to demonstrate that the use of the speech, gesture, handwriting, pointing, spelling jointly may effectively provide recovering from errors or miscommunications, since confusions in one modality usually are unambiguous in another. The paper presents the QuickDoc system, a prototypical application that combines these concepts on multimodal subsystems into a user-friendly multimedia document production technology. For the entire collection see [Zbl 0927.00044].

Cited in

(3)

• Towards a taxonomy of error-handling strategies in recognition-based multi-modal human-computer interfaces
• scientific article; zbMATH DE number 2144105 (Why is no real title available?)
• scientific article; zbMATH DE number 1927250 (Why is no real title available?)

This page was built for publication: Multimodal interfaces for multimedia information agents

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4942764)