OratorPath: An AI-Powered Framework for Enhanced Public Speaking Proficiency

Farwah Aizaz; Laiba Ehsan; Malik Talha Tariq; Shamas Ur Rehman

Authors

Farwah Aizaz Department of Computer Science, HITEC University, Taxila, Pakistan
Laiba Ehsan Department of Computer Science, HITEC University, Taxila, Pakistan
Malik Talha Tariq Department of Computer Science, HITEC University, Taxila, Pakistan
Shamas Ur Rehman Department of Computer Science, HITEC University, Taxila, Pakistan

Keywords:

Public Speaking, Real-Time Feedback, Artificial Intelligence, Human-Computer Interaction, Natural Language Processing, Communication, Educational Technology

Abstract

Public speaking anxiety, commonly referred to as glossophobia, affects an estimated 73-77% of individuals globally, yet most conventional training approaches fail to provide timely, personalized, and holistic feedback. This paper introduces OratorPath, an AI-powered platform that delivers real-time, multimodal feedback on verbal and non-verbal speech-related dimensions. The evaluation dataset consisted of approximately 800 public speaking videos and was divided into 70% training, 15% validation, and 15% testing sets. OratorPath achieved an overall weighted accuracy of 87.73% (95% CI: 85.2%-90.1%, p < 0.001), with component-level results of 92.50% for speech analysis, 92.25% for text processing, and 76.45% for facial and gesture recognition. A one-way ANOVA confirmed statistically significant performance differences between OratorPath and benchmark tools (F(3,796) = 14.27, p < 0.001). Pilot testing with university students showed over 85% self-reported improvement in fluency and reduced reliance on filler words. These results indicate that OratorPath provides a scalable, accessible, and statistically validated framework for public speaking improvement in educational technology, digital communication training, and human–computer interaction.

References

“Social Anxiety Disorder: What You Need to Know - National Institute of Mental Health (NIMH).” Accessed: Apr. 04, 2026. [Online]. Available: https://www.nimh.nih.gov/health/publications/social-anxiety-disorder-more-than-just-shyness

Catherine Nabiem Akpen, Stephen Asaolu, Sunday Atobatele, Hilary Okagbue & Sidney Sampson, “Impact of online learning on student’s performance and engagement: a systematic review,” Discov. Educ., vol. 3, no. 205, 2024, [Online]. Available: https://link.springer.com/article/10.1007/s44217-024-00253-0

“31 Fear Of Public Speaking Statistics (Prevalence).” Accessed: Apr. 04, 2026. [Online]. Available: https://www.crossrivertherapy.com/public-speaking-statistics

T. Pfister and P. Robinson, “Real-time recognition of affective states from nonverbal features of speech and its application for public speaking skill analysis,” IEEE Trans. Affect. Comput., vol. 2, no. 2, pp. 66–78, Apr. 2011, doi: 10.1109/T-AFFC.2011.8.

Benjamin Kommey, Ernest O. Addo, “A Hidden Markov Model-Based Speech Recognition System Using Baum-Welch, Forward-Backward and Viterbi Algorithms,” Jordan J. Electr. Eng., vol. 9, no. 4, p. 509, 2023, doi: 10.5455/jjee.204-1675950756.

D. L. Goodman, Various, and P. Amber Acosta, “Peer Review.” Accessed: Apr. 29, 2026. [Online]. Available: https://open.maricopa.edu/com225/chapter/peer-review/

“The Role of Feedback in Improving Public Speaking Training Skills - Globibo Blog.” Accessed: Apr. 29, 2026. [Online]. Available: https://globibo.blog/the-role-of-feedback-in-improving-public-speaking-training-skills/

N. Petrocchi, C. Ottaviani, and A. Couyoumdjian, “Compassion at the mirror: Exposure to a mirror increases the efficacy of a self-compassion manipulation in enhancing soothing positive affect and heart rate variability,” J. Posit. Psychol., vol. 12, no. 6, pp. 525–536, Nov. 2017, doi: 10.1080/17439760.2016.1209544.

S. V. Jadhav, S. R. Shinde, D. K. Dalal, T. M. Deshpande, A. S. Dhakne, and Y. M. Gaherwar, “Improve Communication Skills using AI,” 2023 Int. Conf. Emerg. Smart Comput. Informatics, ESCI 2023, 2023, doi: 10.1109/ESCI56872.2023.10099941.

J. Huang, “Enhancing EFL Speaking Feedback with ChatGPT’s Voice Prompts,” Int. J. TESOL Stud., vol. 6, no. 3, pp. 4–13, 2024, doi: 10.58304/IJTS.20240302.

Ge Zhu, Juan-Pablo Caceres, Justin Salamon, “Filler Word Detection and Classification: A Dataset and Benchmark,” Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, 2022, [Online]. Available: https://arxiv.org/abs/2203.15135

Emmanuel Akinrintoyo, Nadine Abdelhalim, Nicole Salomons, “WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper,” Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, 2025, [Online]. Available: https://arxiv.org/abs/2505.21551

Annika C. Speer, Valeria G. Dominguez, “Reimagining the Public Speaking Course: Student Experiences and Outcomes in an Online Format,” Trends High Educ., vol. 4, no. 4, p. 75, 2025, doi: https://doi.org/10.3390/higheredu4040075.

“New study uses VR to support people with a fear of public speaking | Brunel University of London.” Accessed: Apr. 29, 2026. [Online]. Available: https://www.brunel.ac.uk/news-and-events/news/articles/New-study-uses-VR-to-treat-people-with-a-fear-of-public-speaking

A. Alasiry, M. Al-Hussain, M. Turki-Hadj Alouane, and N. Ben Hadj-Alouane, “Efficient audio-visual emotion recognition approach,” Multimed. Tools Appl. 2025 8428, vol. 84, no. 28, pp. 33405–33429, Jan. 2025, doi: 10.1007/S11042-024-20572-6.

H. Ranganathan, S. Chakraborty, and S. Panchanathan, “Multimodal emotion recognition using deep learning architectures,” 2016 IEEE Winter Conf. Appl. Comput. Vision, WACV 2016, May 2016, doi: 10.1109/WACV.2016.7477679.

“AI Roleplay Platform for Communication Coaching | Yoodli.” Accessed: Apr. 04, 2026. [Online]. Available: https://yoodli.ai/

“Orai | AI-powered app for practicing your presentations.” Accessed: Apr. 29, 2026. [Online]. Available: https://orai.com/

Pekka Isotalus, Marja Eklund, “Artificial intelligence as a feedback provider in practicing public speaking,” Commun. Teach., vol. 39, pp. 78–85, 2025, [Online]. Available: https://www.tandfonline.com/doi/full/10.1080/17404622.2024.2407910

“VirtualSpeech - AI-Powered Soft Skills Training in VR and Online.” Accessed: Apr. 04, 2026. [Online]. Available: https://virtualspeech.com/

M. E. Jim, J. B. Yap, G. C. Laolao, A. Z. Lim, and J. A. Deja, “Speak with Confidence: Designing an Augmented Reality Training Tool for Public Speaking,” Apr. 2025, Accessed: Apr. 04, 2026. [Online]. Available: http://arxiv.org/abs/2504.11380

Ziqing Zhang, “AI-Powered Intelligent Speech Processing: Evolution, Applications and Future Directions,” Int. J. Adv. Comput. Sci. Appl., vol. 16, no. 2, 2025, [Online]. Available: https://thesai.org/Publications/ViewPaper?Volume=16&Issue=2&Code=IJACSA&SerialNo=91

“AI in Education: The Rise of Intelligent Tutoring Systems | Park University.” Accessed: Apr. 04, 2026. [Online]. Available: https://www.park.edu/blog/ai-in-education-the-rise-of-intelligent-tutoring-systems/

Siyu Fan, Jianan Jing, “Audio-Visual Learning for Multimodal Emotion Recognition,” Symmetry (Basel)., vol. 17, no. 3, p. 418, 2025, doi: https://doi.org/10.3390/sym17030418.

Akbayan Bekarystankyzy, Iglikova Mereilim, “Adaptive Educational Recommendation Systems For Personalized Learning: A Review Of User Modeling And Machine Learning Approaches,” Int. J. Adv. Signal Image Sci., vol. 12, no. 1, pp. 589–609, 2026, doi: 10.29284/mjf4f265.

M. Kaloev and G. Krastev, “Comparative Analysis of Activation Functions Used in the Hidden Layers of Deep Neural Networks,” HORA 2021 - 3rd Int. Congr. Human-Computer Interact. Optim. Robot. Appl. Proc., Jun. 2021, doi: 10.1109/HORA52670.2021.9461312.