Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-1458
Publication type: Conference paper
Type of review: Peer review (publication)
Title: Emotion recognition from speech using representation learning in extreme learning machines
Authors: Glüge, Stefan
Böck, Ronald
Ott, Thomas
DOI: 10.5220/0006485401790185
10.21256/zhaw-1458
Proceedings: Proceedings of the 9th International Joint Conference on Computational Intelligence
Editors of the parent work: Sabourin, Christophe
Julian Merelo, Juan
O'Reilly, Una-May
Madani, Kurosh
Warwick, Kevin
Page(s): 179
Pages to: 185
Conference details: 9th International Joint Conference on Computational Intelligence, Funchal, Portugal, 1-3 November 2017
Issue Date: 2017
Publisher / Ed. Institution: SciTePress
ISBN: 978-989-758-274-5
Language: English
Subjects: Emotion recognition from speech; Representation learning; Extreme learning machine
Subject (DDC): 006: Special computer methods
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.
URI: https://digitalcollection.zhaw.ch/handle/11475/1519
Fulltext version: Published version
License (according to publishing contract): CC BY-NC-ND 4.0: Attribution - Non commercial - No derivatives 4.0 International
Departement: Life Sciences and Facility Management
Organisational Unit: Institute of Computational Life Sciences (ICLS)
Appears in collections:Publikationen Life Sciences und Facility Management

Files in This Item:
File Description SizeFormat 
IJCCI_2017_3.pdf190.19 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.