Speak with Confidence: Designing an Augmented Reality Training Tool for Public Speaking

2025-04-15

AI Summary

This study addresses public speaking anxiety by proposing SpeakAR, a lightweight augmented reality (AR)-based training tool. SpeakAR deploys interactive virtual audiences within everyday environments to enable accessible, highly immersive speech practice. Its key innovations include dynamic facial expression modeling combined with idle animation synthesis to enhance audience realism and user presence, alongside real-time pose rendering and behavior-based feedback for personalized training. Unlike VR-based approaches, SpeakAR significantly improves accessibility and practicality. In an evaluation involving five participants with varying anxiety levels completing six training sessions, self-reported speaking confidence increased significantly (p < 0.05). User feedback further confirmed that dynamic facial expressions critically enhance both immersion and perceived self-efficacy.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Natural Language Processing: Speech
• Humans and AI: Interaction Techniques and Devices

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Public speaking anxiety affects many individuals, yet opportunities for real-world practice remain limited. This study explores how augmented reality (AR) can provide an accessible training environment for public speaking. Drawing from literature on public speaking, VR-based training, self-efficacy, and behavioral feedback mechanisms, we designed SpeakAR, an AR-based tool that simulates audience interaction through virtual models. SpeakAR was evaluated with five participants of varying anxiety levels, each completing six speaking tasks. Results indicate that AR exposure can enhance confidence, with participants finding the system useful for practice. Feedback highlighted the importance of dynamic facial expressions and idle animations in virtual models to improve realism and engagement. Our findings contribute to the design of AR-based training tools for public speaking, offering insights into how immersive environments can support skill development and anxiety reduction.

Problem

• AR tool to reduce public speaking anxiety
• Simulates audience interaction for practice
• Enhances confidence through immersive training

Innovation

• AR-based tool simulates audience interaction
• Dynamic facial expressions enhance realism
• Immersive environment reduces speaking anxiety