Emotion Recognition from Speech using Representation Learning in Extreme Learning Machines

Stefan Glüge, Ronald Böck, Thomas Ott

Abstract

We propose the use of an Extreme Learning Machine initialised as auto-encoder for emotion recognition from speech. This method is evaluated on three different speech corpora, namely EMO-DB, eNTERFACE and SmartKom. We compare our approach against state-of-the-art recognition rates achieved by Support Vector Machines (SVMs) and a deep learning approach based on Generalised Discriminant Analysis (GerDA). We could improve the recognition rate compared to SVMs by 3%-14% on all three corpora and those compared to GerDA by 8%-13% on two of the three corpora.

Download


Paper Citation


in Harvard Style

Glüge S., Böck R. and Ott T. (2017). Emotion Recognition from Speech using Representation Learning in Extreme Learning Machines.In Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI, ISBN 978-989-758-274-5, pages 179-185. DOI: 10.5220/0006485401790185


in Bibtex Style

@conference{ijcci17,
author={Stefan Glüge and Ronald Böck and Thomas Ott},
title={Emotion Recognition from Speech using Representation Learning in Extreme Learning Machines},
booktitle={Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,},
year={2017},
pages={179-185},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006485401790185},
isbn={978-989-758-274-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,
TI - Emotion Recognition from Speech using Representation Learning in Extreme Learning Machines
SN - 978-989-758-274-5
AU - Glüge S.
AU - Böck R.
AU - Ott T.
PY - 2017
SP - 179
EP - 185
DO - 10.5220/0006485401790185