Electronic International Standard Serial Number (EISSN)
The users of Ambient Intelligence systems expect an intelligent behavior from their environment, receiving adapted and easily accessible services and functionality. This can only be possible if the communication between the user and the system is carried out through an interface that is simple (i.e. which does not have a steep learning curve), fluid (i.e. the communication takes place rapidly and effectively), and robust (i.e. the system understands the user correctly). Natural language interfaces such as dialog systems combine the previous three requisites, as they are based on a spoken conversation between the user and the system that resembles human communication. The current industrial development of commercial dialog systems deploys robust interfaces in strictly defined application domains. However, commercial systems have not yet adopted the new perspective proposed in the academic settings, which would allow straightforward adaptation of these interfaces to various application domains. This would be highly beneficial for their use in AmI settings as the same interface could be used in varying environments. In this paper, we propose a new approach to bridge the gap between the academic and industrial perspectives in order to develop dialog systems using an academic paradigm while employing the industrial standards, which makes it possible to obtain new generation interfaces without the need for changing the already existing commercial infrastructures. Our proposal has been evaluated with the successful development of a real dialog system that follows our proposed approach to manage dialog and generates code compliant with the industry-wide standard VoiceXML.
dialog systems; statistical methodologies; voicexml; web interfaces; speech interaction