JAIST Repository >
School of Information Science >
Articles >
Journal Articles >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/14784

Title: Optimizing Fuzzy Inference Systems for Improving Speech Emotion Recognition
Authors: Elbarougy, Reda
Akagi, Masato
Keywords: Fuzzy Inference System (FIS)
Particle swarm optimization
Speech emotion recognition
Optimum clusters radius
Issue Date: 2016-10-18
Publisher: Springer
Magazine name: Advances in Intelligent Systems and Computing
Volume: 533
Start page: 85
End page: 95
DOI: 10.1007/978-3-319-48308-5_9
Abstract: Fuzzy Inference System (FIS) is used for pattern recognition and classification purposes in many fields such as emotion recognition.However, the performance of FIS is highly dependent on the radius of clusters which has a very important role for its recognition accuracy. Although many researcher initialize this parameter randomly which does not grantee the best performance of their systems. The purpose of thispaper is to optimize FIS parameters in order to construct a high efficient system for speech emotion recognition. Therefore, a novel optimizationalgorithm based on particle swarm optimization technique is proposed for finding the best parameters of FIS classifier. In order to evaluate theproposed system it was tested using two emotional speech databases; Fujitsu and Berlin database. The simulation results show that the optimized system has high recognition accuracy for both languages with 97% recogintion acuracy for Japanese and 80% for German database.
Rights: This is the author-created version of Springer, Reda Elbarougy and Masato Akagi, Advances in Intelligent Systems and Computing, 533, 2016, 85-95. The original publication is available at www.springerlink.com, http://dx.doi.org/10.1007/978-3-319-48308-5_9
URI: http://hdl.handle.net/10119/14784
Material Type: author
Appears in Collections:b10-1. 雑誌掲載論文 (Journal Articles)

Files in This Item:

File Description SizeFormat
2215.pdf395KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology