Detecting Speech Disfluencies Using Open-Source Tools in Automatic Feedback Systems for Oral Presentation Training

Willy Mateo, Leonardo Eras, Giancarlo Carvajal, Federico Domínguez, Federico Domínguez

2024

Abstract

In the realm of verbal communication, most common non-clinical speech disfluencies are filler words and filled pauses, which pose challenges for effective oral presentations. Yet their detection is no easy task. This article presents the usage of OpenAI’s Whisper for filled pauses and filler words detection in Spanish oral presentations, including on-the-wild usage with undergraduate students. Preliminary results indicate that Whisper demonstrates promise as a valuable tool to identify a substantial amount of filler words and filled pauses. Despite areas of improvement, Whisper serves as a diagnostic tool for assessing disfluences in oral communication.

Paper Citation

in Harvard Style

Mateo W., Eras L., Carvajal G. and Domínguez F. (2024). Detecting Speech Disfluencies Using Open-Source Tools in Automatic Feedback Systems for Oral Presentation Training. In Proceedings of the 16th International Conference on Computer Supported Education - Volume 2: CSEDU; ISBN 978-989-758-697-2, SciTePress, pages 213-220. DOI: 10.5220/0012622100003693

in Bibtex Style

@conference{csedu24,
author={Willy Mateo and Leonardo Eras and Giancarlo Carvajal and Federico Domínguez},
title={Detecting Speech Disfluencies Using Open-Source Tools in Automatic Feedback Systems for Oral Presentation Training},
booktitle={Proceedings of the 16th International Conference on Computer Supported Education - Volume 2: CSEDU},
year={2024},
pages={213-220},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012622100003693},
isbn={978-989-758-697-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Computer Supported Education - Volume 2: CSEDU
TI - Detecting Speech Disfluencies Using Open-Source Tools in Automatic Feedback Systems for Oral Presentation Training
SN - 978-989-758-697-2
AU - Mateo W.
AU - Eras L.
AU - Carvajal G.
AU - Domínguez F.
PY - 2024
SP - 213
EP - 220
DO - 10.5220/0012622100003693
PB - SciTePress