Title page and visualization from the Beyond Note-Taking research publication
Publication

Beyond Note-Taking

A diarization-aware, transparent and privacy-preserving AI assistant for oral examinations.

Author
Maximilian Dauner, Ricky Liu and Gudrun Socher
Status
Published and presented at IEEE EDUCON 2026
Related capability
Engineer · Enable

Support examiners with richer evidence from oral assessments without automating academic judgment or exporting sensitive material.

Oral examinations reveal reasoning in real time, yet they are difficult to document consistently and leave little time for detailed feedback.

A locally hosted workflow combining audio standardization, diarization, aligned speech recognition, retrieval and language-model analysis.

Human boundary

An initial evaluation compared instructor assessments with the framework across eleven complete student cases and three project milestones; high-stakes use still requires calibration, bias monitoring and explicit oversight.

Inspect the project system
Begin the Impossible

Bring us the idea that still feels impossible.

Tell us what you are trying to make possible. We will help identify the right creative, technical and operational starting point.