Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/44005
Title: Global Selection of Features for Nonlinear Dynamics Characterization of Emotional Speech
Authors: Henríquez Rodríguez, Patricia
Alonso Hernández, Jesús B. 
Ferrer Ballester, Miguel A. 
Travieso González, Carlos M. 
Orozco-Arroyave, Juan R.
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Nonlinear dynamic Emotional speech Forward floating feature selection Neural networks
Issue Date: 2013
Publisher: 1866-9956
Journal: Cognitive Computation 
Abstract: This paper proposes the application of measures based on nonlinear dynamics for emotional speech characterization. Measures such as mutual information, dimension correlation, entropy correlation, Shannon’s entropy, Lempel–Ziv complexity and Hurst exponent are extracted from the samples of a database of emotional speech. Then, summary statistics such as mean, standard deviation, skewness and kurtosis are applied on the extracted measures. Experiments were conducted on the Berlin emotional speech database for a three-class problem (neutral, fear and anger as emotional states). Feature selection is accomplished and a methodology is proposed to find the best features. In order to evaluate the discrimination ability of the selected features, a neural network classifier is used. The global success rate is 93.78 ± 3.18 %.
URI: http://hdl.handle.net/10553/44005
ISSN: 1866-9956
DOI: 10.1007/s12559-012-9157-0
Source: Cognitive Computation[ISSN 1866-9956],v. 5, p. 517-525
Appears in Collections:Artículos
Show full item record

SCOPUSTM   
Citations

4
checked on May 9, 2021

WEB OF SCIENCETM
Citations

2
checked on May 9, 2021

Page view(s)

65
checked on May 11, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



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