A Subset of Acoustic Features for Machine Learning-based and Statistical Approaches in Speech Emotion Recognition

Giovanni Costantini, Valerio Cesarini, Daniele Casali

2022

Abstract

In this paper, a selection of acoustic features, derived from literature and experiments, is presented for emotion recognition. Additionally, a new speech dataset is built by recording the free speech of six subjects in a retirement home, as part of a pilot project for the care of the elder called E-Linus. The dataset is employed along with another widely used set (Emovo) for testing the effectiveness of the selected features in automatic emotion recognition. Thus, two different machine learning algorithms, namely a multi-class SVM and Naïve Bayes, are used. Due to the unbalanced and preliminary nature of the retirement home dataset, a statistical method based on logical variables is also employed on it. The 24 features prove their effectiveness by yielding sufficient accuracy results for the machine learning-based approach on the Emovo dataset. On the other hand, the proposed statistical method is the only one yielding sufficient accuracy and no noticeable bias when testing on the more unbalanced retirement home dataset.

Paper Citation

in Harvard Style

Costantini G., Cesarini V. and Casali D. (2022). A Subset of Acoustic Features for Machine Learning-based and Statistical Approaches in Speech Emotion Recognition. In Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 4: BIOSIGNALS; ISBN 978-989-758-552-4, SciTePress, pages 257-264. DOI: 10.5220/0010912500003123

in Bibtex Style

@conference{biosignals22,
author={Giovanni Costantini and Valerio Cesarini and Daniele Casali},
title={A Subset of Acoustic Features for Machine Learning-based and Statistical Approaches in Speech Emotion Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 4: BIOSIGNALS},
year={2022},
pages={257-264},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010912500003123},
isbn={978-989-758-552-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 4: BIOSIGNALS
TI - A Subset of Acoustic Features for Machine Learning-based and Statistical Approaches in Speech Emotion Recognition
SN - 978-989-758-552-4
AU - Costantini G.
AU - Cesarini V.
AU - Casali D.
PY - 2022
SP - 257
EP - 264
DO - 10.5220/0010912500003123
PB - SciTePress