Toward the development of an integrative framework for multimodal dialogue processing

The "universal accessibility" concept is acquiring an important role in the research area of human-computer interaction (HCI). This phenomenon is guided by the need to simplify the access to technological devices, such as mobile phones, PDAs and portable PCs, by making human-computer interaction more similar to human-human communication. In this direction, multimodal interaction has emerged as a new paradigm of human-computer interaction, which advances the implementation of universal accessibility. The main challenge of multimodal interaction, that is also the main topic of this paper, lies in developing a framework that is able to acquire information derived from whatever input modalities, to give these inputs an appropriate representation with a common meaning, to integrate these individual representations into a joint semantic interpretation, and to understand which is the better way to react to the interpreted multimodal sentence by activating the appropriate output devices. A detailed description of this framework and its functionalities will be given in this paper, along with some preliminary application details.