Minuteman: Machine and Human Joining Forces in Meeting Summarization
This work addresses the challenge of efficient meeting minuting for professionals, though it is incremental as it builds on existing ASR and summarization technologies.
The paper tackles the problem of creating high-quality meeting summaries by addressing errors in automatic speech recognition and summarization models, proposing Minuteman, a semi-automatic tool that reduces cognitive load for notetakers and enables real-time collaborative editing.
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 to absence or a lack of focus. We conduct several tests of the application in varied settings, exploring the worthiness of the concept and the possible user strategies.