PolyPresentation: A Multimodal AI Platform for Slide-Aware Iterative Presentation Practice

📅 2026-08-13
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the limitation of existing AI-powered speech rehearsal tools, which often lack integration with slide content and thus struggle to deliver context-specific, actionable feedback. The paper introduces the first slide-aware, multimodal AI platform for speech practice, which jointly leverages audio, transcript, and visual slide information to create a unified iterative rehearsal loop encompassing per-slide practice, full run-throughs, and simulated Q&A sessions. Crucially, the system anchors its feedback precisely to relevant slide contexts, yielding highly contextualized and actionable guidance. Evaluated on 20 academic presentations, the platform significantly outperforms four baseline systems in terms of feedback contextual relevance, actionability, and rehearsal utility, while demonstrating strong alignment with human expert evaluations.
📝 Abstract
Presentations are essential for students, researchers, and professionals to communicate ideas persuasively, yet delivering them effectively requires repeated practice that coordinates content, delivery, visual materials, and audience interaction. Existing AI-assisted rehearsal tools provide scalable feedback, but they often treat presentations as single-run delivery performances, offering limited support for linking feedback to the slide deck or planning what to practice in the next iteration. To address this gap, we introduce PolyPresentation, a multimodal AI platform for slide-aware iterative presentation practice. PolyPresentation organizes slide-by-slide practice, full rehearsal, audience Q&A, and feedback into a unified practice loop, using slide-grounded evidence to help presenters diagnose performance issues and prepare for subsequent practice. We evaluate PolyPresentation through a rubric-based comparison with four baseline systems on 20 academic presentation rehearsals, and additionally assess its alignment with human ratings. Results suggest that PolyPresentation provides more actionable, context-aware, and practice-oriented support for improving presentations. The demonstration video is available at https://youtu.be/MmWj9O_PJxw.
Problem

Research questions and friction points this paper is trying to address.

presentation practice
slide-aware feedback
iterative rehearsal
multimodal AI
audience interaction
Innovation

Methods, ideas, or system contributions that make the work stand out.

slide-aware
iterative practice
multimodal AI
presentation feedback
practice loop
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
C
Chen Chen
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
J
Jihao Li
Institute for Higher Education Research and Development, The Hong Kong Polytechnic University, Hong Kong, China
Zhiyuan Wen
Zhiyuan Wen
The Hong Kong Polytechnic University
NLP
T
Tianhui Zhang
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, China
Di Zou
Di Zou
Department of English and Communication, The Hong Kong Polytechnic University, Hong Kong, China
Jiannong Cao
Jiannong Cao
IEEE Fellow; Chair Professor, Hong Kong Polytechnic University
Distributed computingMobile and pervasive computingWireless sensor networksCloud computingBig Data