Paper Info
Title
Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study.
Abstract
Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm GSA and its binary version BGSA, respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation PSO algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.
Year
DOI
Venue
2015
10.1080/09540091.2015.1080224
Connect. Sci.
Keywords
Field
DocType
emotion recognition,speech processing,modified Elman neural network,optimisation,gravitational search algorithm,firefly algorithm
Particle swarm optimization,Speech processing,Feature selection,Computational intelligence,Computer science,Algorithm,Firefly algorithm,Artificial intelligence,Classifier (linguistics),Artificial neural network,Genetic algorithm,Machine learning
Journal
Volume
Issue
ISSN
27
4
0954-0091
Citations 
PageRank 
References 
2
0.37
63
Authors
3
Name
Order
Citations
PageRank
Mansour Sheikhan129720.38
Mahdi Abbasnezhad Arabi220.37
Davood Gharavian311710.06