📞 +91-7667918914 | ✉️ iarjset@gmail.com
International Advanced Research Journal in Science, Engineering and Technology
International Advanced Research Journal in Science, Engineering and Technology A Monthly Peer-Reviewed Multidisciplinary Journal
ISSN Online 2393-8021ISSN Print 2394-1588Since 2014
IARJSET aligns to the suggestive parameters by the latest University Grants Commission (UGC) for peer-reviewed journals, committed to promoting research excellence, ethical publishing practices, and a global scholarly impact.
← Back to VOLUME 13, ISSUE 11, NOVEMBER 2026

AI Lecture-to-Notes Generator

Nitin Shravan Yeole, Manoj V. Nikum, Shivam B. Limbhare

👁 6 views📥 4 downloads
Share: 𝕏 f in ✈ ✉
Abstract: Students lose a great deal of attention during lectures because listening, understanding and writing must happen at the same time, and revising from long lecture recordings is slow. This paper presents the design of an AI Lecture-to- Notes Generator that converts lecture audio or video into structured, revisable study notes. The system uses OpenAI Whisper, a transformer-based speech recognition model, to transcribe the lecture. The raw transcript is cleaned by removing filler words and repeated phrases and is divided into topic-wise chunks that fit the input limit of the summarisation model. Each chunk is passed to BART, a transformer sequence-to-sequence model, which produces a concise abstractive summary. The summaries are merged and formatted into headings, bullet points and key terms, and the final notes can be downloaded as a PDF or Word file through a simple web interface. Transcription quality is measured with Word Error Rate (WER) and summary quality with ROUGE scores, together with a comparison against manually written notes. The paper documents the architecture, processing parameters and evaluation protocol, and reviews the published benchmark performance of the two underlying models. The proposed tool aims to save students' time, support better revision and help learners who find real-time note-taking difficult.

Keywords: Lecture to notes, Automatic speech recognition, Whisper, BART, Abstractive text summarisation, Natural language processing, ROUGE, Word Error Rate

How to Cite:

[1] Nitin Shravan Yeole, Manoj V. Nikum, Shivam B. Limbhare, “AI Lecture-to-Notes Generator,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2026.131118

Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.