Smart Minutes of Meeting (SMoM) is an AI-powered system designed to automate the generation of professional meeting minutes from multi-speaker audio recordings. In today's fast-paced, remote-first environments, manual documentation of meetings is time-consuming, error-prone, and inefficient. SMoM addresses this by leveraging advanced speech separation, speaker diarization, and transcription techniques using models like OpenAI Whisper to accurately convert audio into text. It then uses large language models (LLMs) to extract key information and generate a well-structured summary. The system supports speaker label editing, ensuring clarity and personalization in the final minutes. Built using a robust Django backend with Celery for parallel task management and a sleek React frontend, SMoM delivers a seamless user experience. This project demonstrates practical innovation by combining audio signal processing with cutting-edge natural language processing to solve a real-world communication bottleneck for teams, educators, and businesses.
Tools: django,celery,redis,mongodb,aws,react,pyannoteAI,whisper
Department: Department of Computer Science
Project Poster
