The media equation: how people treat computers, television, and new media like real people and places
Gesture and voice prototyping for early evaluations of social acceptability in multimodal interfaces
International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction
| Hi-index | 0.00 |
People just cannot stop being people when they communicate with machines. This is never more true than when they are using spoken language to do so. Current telephone interactive voice technology uses recorded prompts and simple menus to allow callers to use the telephone keypad (TouchTone) to access services. Within this highly structured approach, care still needs to be taken when designing the interface for human behaviour.The technology to enable people to use spoken language to talk with machines is maturing rapidly. As it does, more natural interfaces that emulate ordinary human-human conversation are emerging. As the interfaces become more like people, the behaviours and expectations of those interacting with the machine also become richer. This presents a real design challenge that must be addressed. This paper discusses the different generations of spoken dialogue technologies and discusses how human characteristics must be taken into account with each successive step toward natural conversation.