Effect of sympathetic relation and unsympathetic relation in multi-agent spoken dialogue system

Recently, spoken dialog systems using speech recognition technology have been becoming popular. Such as chat-like dialog systems, these systems which do not have any specific purpose are called “Non-Task-oriented spoken dialog system”. In this study, we focused on non-task-oriented spoken dialog systems. We have developed a multi-party chat-like dialog system with different preferences between two agents. In order to provide more enjoyable chatting to users, we focused on the relationship between two agents. In this study, we dealt with two types of the chat-like dialog system with two agents: an “Unsympathetic dialog system ”where one agent's preference differs from another agent, and a “Sympathetic dialog system” where both agents have the same preference. We evaluated user's degree of satisfaction by using our developed systems. As a result of the experiment, the sympathetic dialog system achieved a better impression in chatting. In order to solve the system problems obtained from the experimental results, we designed a new dialog system in order to deal with a more enjoyable conversation.