In this study a class of Multi-Objective Genetic Algorithms (MOGAs) is proposed to select the most relevant features for the problem of speech-based emotion recognition. The employed evolutionary algorithms are the Strength Pareto Evolutionary Algorithm (or SPEA), the Preference-Inspired CoEvolutionary Algorithm with goal vectors (or PICEA), and the Nondominated Sorting Genetic Algorithm II (or NSGA-II). Performances of the proposed algorithms were compared against conventional feature selection methods on a number of emotional speech corpora. The study revealed that for some of the corpora the proposed approach significantly outperforms the baseline feature selection methods up to 5.4% of relative difference.
Cite as: Sidorov, M., Brester, C., Schmitt, A. (2015) Contemporary stochastic feature selection algorithms for speech-based emotion recognition. Proc. Interspeech 2015, 2699-2703, doi: 10.21437/Interspeech.2015-569
@inproceedings{sidorov15_interspeech,
author={Maxim Sidorov and Christina Brester and Alexander Schmitt},
title={{Contemporary stochastic feature selection algorithms for speech-based emotion recognition}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={2699--2703},
doi={10.21437/Interspeech.2015-569}
}