Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-1458
Title: Emotion recognition from speech using representation searning in extreme learning machines
Authors : Glüge, Stefan
Böck, Ronald
Ott, Thomas
Volume(Issue) : 1
Pages : 179
Pages to: 185
Conference details: 9th International Joint Conference on Computational Intelligence, Funchal, Madeira, Portugal, 1-3 November 2017
Editors of the parent work: Sabourin, Christophe
Julian Merelo, Juan
O'Reilly, Una-May
Madani, Kurosh
Warwick, Kevin
Publisher / Ed. Institution : SciTePress
Publisher / Ed. Institution: Funchal, Madeira, Portugal
Issue Date: 2017
Language : Englisch / English
Subjects : Emotion recognition from speech; Representation learning; Extreme learning machine
Subject (DDC) : 004: Informatik
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.
Departement: Life Sciences und Facility Management
Organisational Unit: Institut für Angewandte Simulation (IAS)
Publication type: Konferenz: Paper / Conference Paper
DOI : 10.5220/0006485401790185
10.21256/zhaw-1458
ISBN: 978-989-758-274-5
URI: http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=AfrkrgkgTj0=&t=1
https://digitalcollection.zhaw.ch/handle/11475/1519
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.