A Comparison of Machine Learning Algorithms and Feature Sets for Automatic Vocal Emotion Recognition in Speech

GND
1305002350
Affiliation
Department of Social Psychology, Institute of Psychology, Friedrich Schiller University Jena, Humboldtstraße 26, 07743 Jena, Germany
Doğdu, Cem;
GND
120936143
Affiliation
Department of Social Psychology, Institute of Psychology, Friedrich Schiller University Jena, Humboldtstraße 26, 07743 Jena, Germany
Kessler, Thomas;
GND
1234175355
Affiliation
Department of Social Psychology, Institute of Psychology, Friedrich Schiller University Jena, Humboldtstraße 26, 07743 Jena, Germany
Schneider, Dana;
GND
1234174863
ORCID
0000-0001-6455-2400
Affiliation
Computer Vision Group, Department of Mathematics and Computer Science, Friedrich Schiller University Jena, 07743 Jena, Germany
Shadaydeh, Maha;
GND
1150679573
ORCID
0000-0001-5762-0188
Affiliation
Department of General Psychology and Cognitive Neuroscience, Friedrich Schiller University Jena, Am Steiger 3/Haus 1, 07743 Jena, Germany
Schweinberger, Stefan R.

Vocal emotion recognition (VER) in natural speech, often referred to as speech emotion recognition (SER), remains challenging for both humans and computers. Applied fields including clinical diagnosis and intervention, social interaction research or Human Computer Interaction (HCI) increasingly benefit from efficient VER algorithms. Several feature sets were used with machine-learning (ML) algorithms for discrete emotion classification. However, there is no consensus for which low-level-descriptors and classifiers are optimal. Therefore, we aimed to compare the performance of machine-learning algorithms with several different feature sets. Concretely, seven ML algorithms were compared on the Berlin Database of Emotional Speech: Multilayer Perceptron Neural Network (MLP), J48 Decision Tree (DT), Support Vector Machine with Sequential Minimal Optimization (SMO), Random Forest (RF), k-Nearest Neighbor (KNN), Simple Logistic Regression (LOG) and Multinomial Logistic Regression (MLR) with 10-fold cross validation using four openSMILE feature sets (i.e., IS-09, emobase, GeMAPS and eGeMAPS). Results indicated that SMO, MLP and LOG show better performance (reaching to 87.85%, 84.00% and 83.74% accuracies, respectively) compared to RF, DT, MLR and KNN (with minimum 73.46%, 53.08%, 70.65% and 58.69% accuracies, respectively). Overall, the emobase feature set performed best. We discuss the implications of these findings for applications in diagnosis, intervention or HCI.

Cite

Citation style:
Could not load citation form.

Rights

License Holder: © 2022 by the authors.

Use and reproduction: