A distributed agent architecture for intelligent multi-domain spoken dialogue systems

Multi-domain spoken dialogue systems with high degree of intelligence and d omain extensibility have long been desired but difficult to achieve. When t he user freely surfs among different topics during the dialogue, it will be very difficult for the system to control the switching of the topics and d omains while keeping the dialogue consistent, and decide when and how to ta ke the initiative. This paper presents a distributed agent architecture for multi-domain spoken dialogue systems with high domain extensibility and in telligence. Under this architecture, different spoken dialogue agents (SDA' s) handling different domains can be developed independently, and then smoo thly cooperate with one another to achieve the user's multiple goals, while a user interface agent (UIA) can access the correct spoken dialogue agent through a domain switching protocol, and carry over the dialogue state and history so as to keep the knowledge processed coherently across different d omains.