AUTOMATIC MEETING MINUTES GENERATION USING MULTI-SPEAKER DIALOGUE SUMMARIZATION.

The Automatic Meeting Minutes Generation project provides a practical solution for converting live meeting conversations into structured, exportable minutes. By integrating authentication, meeting scheduling, live room management, Web RTC communication, Web Socket synchronization, speech capture, transcript storage, NLP-based extraction, and document export, the system covers the full workflow of modern meeting documentation.       The research shows that useful meeting minutes do not depend only on transcription. They require participant-aware organization, action item identification, decision highlighting, summary generation, and readable output formatting.     The Meet Minutes implementation addresses these needs through a transparent service-based architecture and a lightweight NLP pipeline. The generated minutes include overall summary, decisions, key points, action items, speaker summaries, person-to-person summaries, and transcript-based evidence.       The system is especially suitable for academic project demonstrations, small teams, classroom discussions, project reviews, and remote collaboration scenarios. Its modular architecture allows future enhancement with machine learning models, cloud speech recognition, advanced diarization, semantic search, calendar integration, role-based access control, and analytics dashboards.       In conclusion, the project successfully demonstrates an end-to-end approach to automatic meeting minutes generation. It reduces manual effort, improves accountability, and transforms unstructured meeting dialogue into organized knowledge that can be reviewed, shared, and archived.

1. Carletta, J., Ashby, S., Bourban, S., Flynn, M., Guillemot, M., Hain, T., Kadlec, J., Karaiskos, V., Kraaij, W., Kronenthal, M., Lathoud, G., Lincoln, M., Lisowska, A., McCowan, I., Post, W., Reidsma, D., and Wellner, P. (2005). The AMI Meeting Corpus: A pre-announcement. Machine Learning for Multimodal Interaction.   2. McCowan, I., Carletta, J., Kraaij, W., Ashby, S., Bourban, S., Flynn, M., Guillemot, M., Hain, T., Kadlec, J., Karaiskos, V., Kronenthal, M., Lathoud, G., Lincoln, M., Lisowska, A., Post, W., Reidsma, D., and Wellner, P. (2005). The AMI Meeting Corpus. International Conference on Methods and Techniques in Behavioral Research.   3. Murray, G., Renals, S., and Carletta, J. (2005). Extractive summarization of meeting recordings. Proceedings of Interspeech.   4. Xie, S., and Liu, Y. (2008). Using corpus and knowledge-based similarity measure in maximum marginal relevance for meeting summarization. IEEE International Conference on Acoustics, Speech and Signal Processing.   5. Purver, M., Ehlen, P., and Niekrasz, J. (2007). Detecting action items in multi-party meetings: Annotation and initial experiments. Proceedings of the SIGdial Workshop on Discourse and Dialogue.   6. Janin, A., Baron, D., Edwards, J., Ellis, D., Gelbart, D., Morgan, N., Peskin, B., Pfau, T., Shriberg, E., Stolcke, A., and Wooters, C. (2003). The ICSI Meeting Corpus. Proceedings of ICASSP.   7. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems.   8. Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., and Zettlemoyer, L. (2020). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. ACL.   9. Zhang, J., Zhao, Y., Saleh, M., and Liu, P. J. (2020). PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization. ICML.   10. Jurafsky, D., and Martin, J. H. (2023). Speech and Language Processing. Draft textbook, Stanford University.