FairTalk: Facilitating Balanced Participation in Video Conferencing by Implicit Visualization of Predicted Turn-Grabbing Intention

2025/05/26 by Iijima, Ryo, Yoshida, Shigeo, Hashimoto, Atsushi +1
#FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · doi:10.48550/arxiv.2505.20138

Abstract

Creating fair opportunities for all participants to contribute is a notable challenge in video conferencing. This paper introduces FairTalk, a system that facilitates the subconscious redistribution of speaking opportunities. FairTalk predicts participants' turn-grabbing intentions using a machine learning model trained on web-collected videoconference data with positive-unlabeled learning, where turn-taking detection provides automatic positive labels. To subtly balance speaking turns, the system visualizes predicted intentions by mimicking natural human behaviors associated with the desire to speak. A user study suggests that FairTalk may help improve speaking balance, though subjective feedback indicates no significant perceived impact. We also discuss design implications derived from participant interviews.

Citations

• Optuna: A Next-generation Hyperparameter Optimization Framework
• Learning to Generalize: Meta-Learning for Domain Generalization
• Positive-Unlabeled Learning with Non-Negative Risk Estimator
• A simplest systematics for the organization of turn-taking for conversation

Related

• EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild
• Fairness in Rating Prediction by Awareness of Verbal and Gesture Quality of Public Speeches
• The Right to Talk: An Audio-Visual Transformer Approach
• Audio-Visual Evaluation of Oratory Skills
• FairyTED: A Fair Rating Predictor for TED Talk Data