Guardian Eye-AI-Powered Meeting Analyser

The proposed GuardianEye AI Meeting Analyzer provides an intelligent and structured approach to analysing meetings and understanding participant performance. The system combines meeting audio, video, speech-to-text conversion, Natural Language Processing, facial and behavioural analysis, and Machine Learning techniques to study both verbal and non-verbal communication. It supports live online meetings as well as pre-recorded meeting videos, making it useful for different types of professional meetings and discussions.     GuardianEye goes beyond basic meeting recording and summary generation by analysing important factors such as communication quality, participation, engagement, confidence, leadership behaviour, filler words, facial expressions, eye contact, and speaking patterns. Machine Learning algorithms such as Decision Tree and Random Forest are used to support participant evaluation and scoring. The results are presented through an analytics dashboard with meeting summaries, participant insights, performance scores, and reports.     Overall, the proposed system helps users understand meetings more effectively without manually reviewing the entire recording. By combining different types of meeting information in one platform, GuardianEye can provide meaningful communication and behavioural insights. The system can be further improved in the future by using larger datasets, more advanced models, improved emotion recognition, and additional meeting analysis features to provide more accurate and useful results.  

  1.  Hsieh, W. Y., Tsai, H. C., Chen, L. A., & İk, T. U. (2024). Developing an Interview Recording System with Speaker Recognition and Emotion Classification.   2.  Heo, S., Kyung, J., & Chang, J. H. (2024). Multimodal Emotion Recognition with Target Speaker-Based Facial Embeddings.   3.  Li, J., & Peng, J. (2024). End-to-End Multimodal Emotion Recognition Based on Facial Expressions and Remote Photoplethysmography Signals.   4.  Khaoula, T., & Soltane, M. (2025). Deep Learning Based Student Engagement Detection Using Eye Tracking.   5.  Xu, Y., Yu, Y., & Wu, B. (2025). Facial Expression Recognition Based on Inception Network Module.   6.  Kachhoria, R., Daga, N., Ramteke, H., Akotkar, Y., & Ghule, S. (2023). Minutes of Meeting Generation for Online Meetings Using NLP & ML Techniques.   7.  Slovenian End-to-End Automatic Speech Recognition and the Analysis of Emotional Speech.   8.  Oleti, B. L., Prakaash, R. A. D., RanjithKumar, G. S., Reddy, P. P., Narendatta, N., & Vignesh, C. C. (2025). INSIGHTMEET: An AI Powered Meeting Summarizer with Emotion Analytics and Interaction-Mapping. 9.  Srivastav, K., Sharma, S., Srivastava, M., & Singhal, K. (2024). Decoding Communication: Confidence Assessment through CNN-based Speech Signals Analysis.   10. Wenskovitch, J., Fallon, C., Miller, K., & Dasgupta, A. (2024). Characterizing Interaction Uncertainty in Human-Machine Teams.