Serendipity Wall: A Discussion Support System Using Real-time Speech Recognition and Large Language Model

Group discussions are important for exploring new ideas. Discussion support systems will enhance human creative ability through better discussion experiences. One method to support discussions is presenting relevant keywords or images. However, the context of the conversation and information tended not to be taken into account. Therefore, we propose a system that develops group discussions by presenting related information in response to discussions. As a specific example, this study addressed academic discussions among HCI researchers. During brainstorming sessions, the system continuously transcribes the dialogue and generates embedding vectors of the discussions. These vectors are matched against those of existing research articles to identify relevant studies. Then, the system presented relevant studies on the screen with summaries by an LLM. In case studies, this system had the effect of broadening the topics of discussion and facilitating the acquisition of new knowledge. This study showed the possibility that AI can facilitate discussion by providing discussion support through information retrieval and summarizing.