Minuteman: Machine and Human Joining Forces in Meeting Summarization
Franti\v{s}ek Kmje\v{c}, Ond\v{r}ej Bojar

TL;DR
Minuteman is a semi-automatic meeting summarization tool that combines live transcripts and summaries, allowing collaborative editing to improve accuracy and reduce cognitive load during meetings.
Contribution
It introduces a novel interactive system that integrates real-time speech recognition and summarization with user editing to enhance meeting note-taking.
Findings
Effective in reducing cognitive load for notetakers
Enables real-time correction of ASR errors and summaries
Supports varied user strategies in different settings
Abstract
Many meetings require creating a meeting summary to keep everyone up to date. Creating minutes of sufficient quality is however very cognitively demanding. Although we currently possess capable models for both audio speech recognition (ASR) and summarization, their fully automatic use is still problematic. ASR models frequently commit errors when transcribing named entities while the summarization models tend to hallucinate and misinterpret the transcript. We propose a novel tool -- Minuteman -- to enable efficient semi-automatic meeting minuting. The tool provides a live transcript and a live meeting summary to the users, who can edit them in a collaborative manner, enabling correction of ASR errors and imperfect summary points in real time. The resulting application eases the cognitive load of the notetakers and allows them to easily catch up if they missed a part of the meeting due…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech and dialogue systems · Topic Modeling · Natural Language Processing Techniques
