Benchmarking Classification Models for Emotion Recognition in Natural Speech: a Multi-Corporal Study
Document Type
Conference Paper
Rights
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
Disciplines
Computer Sciences
Abstract
A significant amount of the research on automatic emotion recognition from speech focuses on acted speech that is produced by professional actors. This approach often leads to overoptimistic results as the recognition of emotion in real-life conditions is more challenging due the propensity of mixed and less intense emotions in natural speech. The paper presents an empirical study of the most widely used classifiers in the domain of emotion recognition from speech, across multiple non-actedemotional speech corpora. The results indicate that Support Vector Machines have the best performance and that they along with Multi-Layer Perceptron networks and k-nearest neighbour classifiers perform significantly better (using the appropriate statistical tests) than decision trees, Naıve Bayes classifiers and Radial Basis Function networks.
DOI
https://doi.org/10.1109/FG.2011.5771359
Recommended Citation
Tarasov, A., Delany, S. (2011) Benchmarking Classification Models for Emotion Recognition in Natural Speech: a Multi-Corporal Study. EmoSPACE Workshop (in conjunction with IEEE FG 2011 conference), Santa Barbara, 24 March. doi:10.1109/FG.2011.5771359
Funder
Science Foundation Ireland
Publication Details
Presented at the EmoSPACE 2011 workshop (in conjunction with IEEE FG 2011 conference)
Santa Barbara, 24 March, 2011.