Beyond Conversational Discourse: A Framework for Collaborative Dialogue Analysis.

In the collaboration scenario, video calls can not only improve the understanding of the collaborative conversation content but also assist group members in coordinating tasks reasonably and obtaining richer collaboration information. Although they can share or view the recorded call video repeatedly, with the increase in video duration or the influence of surrounding noise, the audio-visual information contained in the collaborative conversation becomes more complex and difficult to understand. So, it's a great challenge for group members to obtain information about the collaboration topic. This paper starts with the video calls in collaborative scenarios and analyzes its interpretable elements from the obtained audio-visual dialogue information. Based on the TM-CTC model (CTC Transformer) and FaceNet algorithm, we construct a framework for deep audio-visual dialogue analysis in the Collaborative Working Environment (CWE). Subsequently, according to the framework mentioned above, we build a collaborative audio-visual dialogue server that is further applied to CWEs to analyze the video calls, generate audio-visual dialogue elements, and present the results to team members. Finally, an application example is utilized to analyze the audio-visual dialogue produced in collaborative video communications. The results show that our proposed framework can improve communication efficiency in team collaboration to a certain extent.