Stress Detection Through Speech Analysis

Kevin Tomba, Joel Dumoulin, Elena Mugellini, Omar Abou Khaled, Salah Hawila

Abstract

The work presented in this paper uses speech analysis to detect candidates stress during HR (human resources) screening interviews. Machine learning is used to detect stress in speech, using the mean energy, the mean intensity and Mel-Frequency Cepstral Coefficients (MFCCs) as classification features. The datasets used to train and test the classification models are the Berlin Emotional Database (EmoDB), the Keio University Japanese Emotional Speech Database (KeioESD) and the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). The best results were obtained with Neural Networks with accuracy scores for stress detection of 97.98% (EmoDB), 95.83% (KeioESD) and 89.16% (RAVDESS).

Download


Paper Citation


in Harvard Style

Tomba K., Dumoulin J., Mugellini E., Abou Khaled O. and Hawila S. (2018). Stress Detection Through Speech Analysis.In Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: ICETE, ISBN 978-989-758-319-3, pages 394-398. DOI: 10.5220/0006855803940398


in Bibtex Style

@conference{icete18,
author={Kevin Tomba and Joel Dumoulin and Elena Mugellini and Omar Abou Khaled and Salah Hawila},
title={Stress Detection Through Speech Analysis},
booktitle={Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: ICETE,},
year={2018},
pages={394-398},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006855803940398},
isbn={978-989-758-319-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: ICETE,
TI - Stress Detection Through Speech Analysis
SN - 978-989-758-319-3
AU - Tomba K.
AU - Dumoulin J.
AU - Mugellini E.
AU - Abou Khaled O.
AU - Hawila S.
PY - 2018
SP - 394
EP - 398
DO - 10.5220/0006855803940398