Comparative analysis of LDA, QDA, SVM, algorithms and neural networks for boredom and fear detection in speech

Bojan Prlinčević; Zoran Milivojević; Milan Mišić; Dejan Gurešić; Dijana Kostić

doi:10.71159/icemit2565P

Authors

Bojan Prlinčević Kosovo and Metohija Academy of Applied Studies, Leposavić, Serbia
Zoran Milivojević Academy of Applied Technical and Preschool studies, Niš, Serbia
Milan Mišić Kosovo and Metohija Academy of Applied Studies, Leposavić, Serbia
Dejan Gurešić University of Priština in Kosovska Mitrovica, Faculty of Sciences and Mathematics, Serbia
Dijana Kostić Šargan inženjering d.o.o, Niš, Serbia

DOI:

https://doi.org/10.71159/icemit2565P

Keywords:

speech emotion recognition, fundamental frequency, neural networks

Abstract

This paper presents an analysis of speech emotion recognition focusing on distinguishing between boredom and fear emotional states. The methodology employs the fundamental frequency trajectory (F₀) and its derivatives to extract characteristics. Emotional states are classified using four machine learning algorithms: Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machines (SVM), and Artificial Neural Networks (ANN). The experiment utilizes the Berlin Emotional Speech Database for training and evaluation. Results demonstrate that all classifiers effectively separate boredom and fear emotions, with ANN achieving the highest classification accuracy. Performance analysis are derived using confusion matrix analysis confirm. This study provides an efficient framework for detecting subtle emotional differences in speech signals, particularly between boredom and fear manifestations.

References

Ayadi, M. E., Kamel, M. S., & Karray, F. (2011). Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern Recognition, 44(3), 572–587. https://doi.org/10.1016/j.patcog.2010.09.020

Berlin Database of Emotional Speech. (2005). Technische Universität Berlin. https://www.tu.berlin/en/kw/research/projects/emotional-speech

Boersma, P., & Weenink, D. (2023). Praat: Doing phonetics by computer (Version 6.3.09) [Computer software]. https://www.praat.org

Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., & Weiss, B. (2005). A database of German emotional speech. In Proceedings of Interspeech (pp. 1517–1520).

Cairns, D., & Hansen, J. H. L. (1994). Nonlinear analysis and detection of speech under stressed conditions. Journal of the Acoustical Society of America, 96(6), 3392–3400. https://doi.org/10.1121/1.410601

Lee, C. M., & Narayanan, S. S. (2005). Toward detecting emotions in spoken dialogs. IEEE Transactions on Speech and Audio Processing, 13(2), 293–303. https://doi.org/10.1109/TSA.2004.838534

Prlinčević, B., Milivojević, Z., & Simović, V. (2023). Estimation of emotions normal/anxiety by fundamental frequency trajectory analysis. KNOWLEDGE – International Journal, 58(3), 495–500.

Tolkmitt, F. J., & Scherer, K. R. (1986). Effect of experimentally induced stress on vocal parameters. Journal of Experimental Psychology: Human Perception and Performance, 12(3), 302–313. https://doi.org/10.1037/0096-1523.12.3.302

Ververidis, D., & Kotropoulos, C. (2006). Emotional speech recognition: Resources, features, and methods. Speech Communication, 48(9), 1162–1181. https://doi.org/10.1016/j.specom.2006.04.003

Wanare, A. P., & Dandare, S. N. (2014). Human emotion recognition from speech. International Journal of Engineering Research and Applications, 4(7), 74–78.