Predicting User Attention using Eye Gaze in Conversational Interfaces
نویسندگان
چکیده
In a conversational system, determining the user’s focus of attention is crucial to the success of the system. Motivated by previous psycholinguistic findings, we are currently examining how eye gaze contributes to automated identification of user attention during conversation. In particular, we are developing techniques that can predict an objects’ activation in a given time frame based on user eye gaze behavior. The predicated object activation can be combined with speech input to better identify user attention. This paper describes our on-going effort on this topic.
منابع مشابه
Eye Gaze for Attention Prediction in Multimodal Human-Machine Conversation
In a conversational system, determining a user’s focus of attention is crucial to the success of the system. Motivated by previous psycholinguistic findings, we are currently examining how eye gaze contributes to automated identification of user attention during humanmachine conversation. As part of this effort, we investigate the contributing roles of various features that are extracted from e...
متن کاملThe Role of Eye Gaze in Avatar Mediated Conversational Interfaces
As we begin to create synthetic characters (avatars) for computer users, it is important to pay attention to both the look and the behavior of the avatar’s eyes. In this paper we present behavior models of eye gaze patterns in the context of real-time verbal communication. We apply these eye gaze models to simulate eye movements in a computergenerated avatar in a number of task settings. We als...
متن کاملEye Gaze for Reference Resolution in Multimodal Conversational Interfaces
EYE GAZE FOR REFERENCE RESOLUTION IN MULTIMODAL CONVERSATIONAL INTERFACES
متن کاملAn Exploration of Eye Gaze in Spoken Language Processing for Multimodal Conversational Interfaces
Motivated by psycholinguistic findings, we are currently investigating the role of eye gaze in spoken language understanding for multimodal conversational systems. Our assumption is that, during human machine conversation, a user’s eye gaze on the graphical display indicates salient entities on which the user’s attention is focused. The specific domain information about the salient entities is ...
متن کاملKnow what I ' m talking about ? Dual eye - tracking in multimodal reference resolution
Multimodal reference resolution is an important component of intelligent user interfaces using natural language. We use multimodal context data – including dyadic gaze to develop models to identify reference in natural conversation. Our approach uses a mixture of rule-based and automatically coded gaze-based, linguistic, spatial, and temporal features, and conversational conditions. We accurate...
متن کامل