Speech emotion classification using fractal dimension-based features
Articles
Gintautas Tamulevičius
Vilnius University
Rasa Karbauskaitė
Vilnius University
Gintautas Dzemyda
Vilnius University
https://orcid.org/0000-0003-2914-1328
Published 2019-09-26
https://doi.org/10.15388/NA.2019.5.1
PDF

Keywords

fractal dimension
speech emotion
feature selection

How to Cite

Tamulevičius G., Karbauskaitė R. and Dzemyda G. (2019) “Speech emotion classification using fractal dimension-based features”, Nonlinear Analysis: Modelling and Control, 24(5), pp. 679–695. doi: 10.15388/NA.2019.5.1.

Abstract

During the last 10–20 years, a great deal of new ideas have been proposed to improve the accuracy of speech emotion recognition: e.g., effective feature sets, complex classification schemes, and multi-modal data acquisition. Nevertheless, speech emotion recognition is still the task in limited success. Considering the nonlinear and fluctuating nature of the emotional speech, in this paper, we present fractal dimension-based features for speech emotion classification. We employed Katz, Castiglioni, Higuchi, and Hurst exponent-based features and their statistical functionals to establish the 224-dimensional full feature set. The dimension was downsized by applying the Sequential Forward Selection technique. The results of experimental study show a clear superiority of fractal dimension-based feature sets against the acoustic ones. The average accuracy of 96.5% was obtained using the reduced feature sets. The feature selection enabled us to obtain the 4-dimensional and 8-dimensional sets for Lithuanian and German emotions, respectively.

PDF
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Please read the Copyright Notice in Journal Policy

Most read articles by the same author(s)