An Agent-Based Architecture for a Multimodal Interface
نویسنده
چکیده
This paper concerns a multimodal interface for designing graphics. The human-machine interaction is achieved by using a pen computer connected to a speech recognition device. The user and the computer cooperate: the user sketches graphics with the pen, the computer understands the user's intention and displays an accurate version of the hand-sketched drawing. The final document is produced sequentially through a process of thinking and drawing. An agent-based architecture implements a multimodal interface with rapidly displayed feedback, supports a cooperative incremental design and adapts the interaction to the user style. At present, an initial application has been developed for drawing tables.
منابع مشابه
A multimodal dialogue interface for flexible tutoring systems
This paper presents an environment for the design and implementation of an Intelligent Tutoring System based on a multimodal dialogue interface and user modelling. The system exploits existing web-based on-line courses and superimposes a rhetorical structure as the underlying model for the course content. In addition, the learner profile is based on the notion of stereotypical ascription, while...
متن کاملMAUI: a Multimodal Affective User Interface Sensing User’s Emotions based on Appraisal Theory - Questions about Facial Expressions..
We are developing a Multimodal Affective User Interface (MAUI) framework shown in Figure 1 and described in [5], aimed at recognizing its users emotions by sensing their various user-centered modalities (or modes), and at giving the users context-aware feedback via an intelligent affective agent by using different agent-centered modes. The agent is built on an adaptive system architecture which...
متن کاملGeneric Pipelined Multi-Agents Architecture for Multimedia Multimodal Software Environments
Multimodal human-computer interaction needs intelligent architectures in order to enhance the flexibility and naturelness of the user interface. These architectures have the ability to manage several multithreaded input signals from different input media in order to perform their fusion into intelligent commands. In this paper, a generic comprehensive agent-based architecture for multimodal eng...
متن کاملTask-Oriented Synergistic Multimodality
Multimodal interface aims at overcoming the shortcomings of conventional human-computer communication -serialized input, excessive accuracy, and low input efficiency -by exploiting the complementary nature of multiple modalities in interpreting user intent, thus improving the efficiency and naturalness of humancomputer interaction. In this paper, we present motivations driving multimodal interf...
متن کاملSpoken and Multimodal Bus Timetable Systems: Design, Development and Evaluation
We present three speech-based bus timetable systems with different approaches. The first system had open user-initiative dialogues aiming at natural interaction. The user tests revealed several problems with this approach, and we developed solutions from multiple perspectives to overcome the problems. The second system focuses on task-oriented system-initiative dialogues, and contains a multimo...
متن کامل