A Name-Triggered AI Voice Scoring System for Enhancing Attentive Listening and Verbal Participation in Primary Classrooms

Enhancing students’ classroom behavior—particularly attentive listening and active verbal participation—remains a fundamental challenge in primary education. This paper introduces a name-triggered AI voice scoring system that leverages real-time speech recognition to evaluate individual student performance during live classroom instruction. The system is built upon a dual-dimensional evaluation model, capturing both listening discipline and verbal engagement. Teachers can call on students by name, and the system—using a custom-trained speech model—automatically identifies the student through voice input and triggers behavior-based scoring. Listening behavior is assessed by monitoring students’ attentiveness and respect during peer and teacher talk, while verbal participation is evaluated based on the use of lesson-specific keywords in students’ spoken responses. The system provides weighted scores, visual feedback, and end-of-class summaries to support formative assessment. Preliminary classroom trials indicate that the system encourages more respectful listening and purposeful speaking behaviors while reducing teacher burden in classroom management and feedback delivery. This research demonstrates the potential of name-triggered voice recognition to personalize classroom analysis and enhance behavioral and learning outcomes in early education.