Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{192466,
        author = {Aniket Kasav and Bhumi Nikam and Vaishnavi Patil and Prof. V. P. Sahane},
        title = {SMART MEETING ASSISTANT AND PERFORMANCE TRACKER FOR ONLINE MEETINGS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {1698-1704},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192466},
        abstract = {The widespread use of virtual meeting platforms in professional, academic, and organizational settings has reshaped modern communication and collaboration. Although tools such as Zoom, Google Meet, and Microsoft Teams offer reliable audio–video connectivity, they provide limited support for intelligent analysis of meeting content. Consequently, participants often struggle with manual note-taking, missed discussion points, unclear accountability, and subjective evaluation of participation.
This review paper examines the evolution of Smart Meeting Assistant and Performance Tracking systems that employ Artificial Intelligence (AI), Natural Language Processing (NLP), and Machine Learning (ML) to improve the effectiveness of online meetings. The study reviews existing research on speech-to-text transcription, dialogue analysis, extractive and abstractive summarization techniques, participant performance measurement, and voice-based interaction. It also identifies key research gaps and highlights the limitations of current solutions that operate as isolated or feature-specific tools.
Furthermore, the paper presents the Smart Meeting Assistant and Performance Tracker as an integrated AI-driven framework that combines real-time transcription, automated meeting summarization, speaker-level performance analysis, and voice-command control within a unified platform. By reducing cognitive load and enabling structured, data-driven insights, the proposed approach enhances meeting transparency, engagement assessment, and decision-making. This review provides a foundation for the development of next-generation intelligent meeting systems capable of transforming virtual collaboration into an organized, efficient, and insightful process.},
        keywords = {— Smart Meeting Assistant, Artificial Intelligence, Natural Language Processing, Speech Recognition, Meeting Summarization, Performance Tracking, Voice Commands.},
        month = {February},
        }