This paper proposes a topic visualization system for unfamiliar couples in face-to-face conversations. Some of people are weak at making face-to-face conversations with people for the first time. It is so hard to find good topics for conversations. If any topic can not be found, a non-speech section will come to a conversation and will make them be more awkward. The proposed system visualizes topics to users. As inputting the user's profile data into the system, conversation topics are visualized by referring the input. The proposed system recognizes their speeches in conversations, and detects non-speech sections in their conversation. If a non-speech section is detected, the system switches topics to new ones and presents the new topics to the users. They can continue their conversations if nonspeech sections come more than one time. We experimented the efficiency of the proposed system in decreasing non-speech time in conversations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.