An automatic dialogue generation platform for personalized dialogue applications

Abstract We explore a voice user interface for human–machine communication that uses a dialogue structure personalized to an individual user, subject to the constraints of the system's resources. Conventional dialogue systems typically use architectures that create a set of predefined speech objects, or subdialogues, by combining several static components, such as grammars and other language components. Such systems are limited because most databases are dynamic, and users have different preferences for topical content and presentation format. Ideally, a dialogue would combine a user's intentions, encoded in a profile, with information and services available in a dynamic and distributed external environment. We use a modular architecture where a centralized Application Generator (AG) interacts with two managers. A user's preferences are stored in a profile handled by a Profile Manager. An Information Manager uses these preferences when accessing external databases and extracting, filtering, or presenting information in a form customized to that particular user. The AG then builds an anticipated dialogue, allowing a user to navigate between a personalized set of services, each of which presents information and services in a manner customized for that user. Therefore, the AG generates, in a uniform and consistent manner, a finite state dialogue for any task described by a set of specifications residing on a distributed network. Finally, a dialogue manager uses a set of protocols to carry out an actual dialogue session with the user.