Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition

Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition

The selection of feature subset is a crucial aspect in speech emotion recognition problem. In this paper, a Reordering Features with Weights Fusion (RFWF) algorithm is proposed for selecting more effective and compact feature subset. The RFWF algorithm fuses the weights reflecting the relevance, com...

Full description

Bibliographic Details
Main Authors: Xiaoqing Jiang, Kewen Xia, Lingyin Wang, Yongliang Lin
Format: Article
Language:English
Published: Hindawi Limited 2017-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2017/8709518
id doaj-56dd8b4d2ca54dc6b38bf2f045c2cd58
record_format Article
spelling doaj-56dd8b4d2ca54dc6b38bf2f045c2cd582021-07-02T10:10:31ZengHindawi LimitedJournal of Electrical and Computer Engineering2090-01472090-01552017-01-01201710.1155/2017/87095188709518Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion RecognitionXiaoqing Jiang0Kewen Xia1Lingyin Wang2Yongliang Lin3School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Information Science and Engineering, University of Jinan, Shandong, Jinan 250022, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaThe selection of feature subset is a crucial aspect in speech emotion recognition problem. In this paper, a Reordering Features with Weights Fusion (RFWF) algorithm is proposed for selecting more effective and compact feature subset. The RFWF algorithm fuses the weights reflecting the relevance, complementarity, and redundancy between features and classes comprehensively and implements the reordering of features to construct feature subset with excellent emotional recognizability. A binary-tree structured multiple-kernel SVM classifier is adopted in emotion recognition. And different feature subsets are selected in different nodes of the classifier. The highest recognition accuracy of the five emotions in Berlin database is 90.549% with only 15 features selected by RFWF. The experimental results show the effectiveness of RFWF in building feature subset and the utilization of different feature subsets for specified emotions can improve the overall recognition performance.http://dx.doi.org/10.1155/2017/8709518
collection DOAJ
language English
format Article
sources DOAJ
author Xiaoqing Jiang
Kewen Xia
Lingyin Wang
Yongliang Lin
spellingShingle Xiaoqing Jiang
Kewen Xia
Lingyin Wang
Yongliang Lin
Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition
Journal of Electrical and Computer Engineering
author_facet Xiaoqing Jiang
Kewen Xia
Lingyin Wang
Yongliang Lin
author_sort Xiaoqing Jiang
title Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition
title_short Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition
title_full Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition
title_fullStr Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition
title_full_unstemmed Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition
title_sort reordering features with weights fusion in multiclass and multiple-kernel speech emotion recognition
publisher Hindawi Limited
series Journal of Electrical and Computer Engineering
issn 2090-0147
2090-0155
publishDate 2017-01-01
description The selection of feature subset is a crucial aspect in speech emotion recognition problem. In this paper, a Reordering Features with Weights Fusion (RFWF) algorithm is proposed for selecting more effective and compact feature subset. The RFWF algorithm fuses the weights reflecting the relevance, complementarity, and redundancy between features and classes comprehensively and implements the reordering of features to construct feature subset with excellent emotional recognizability. A binary-tree structured multiple-kernel SVM classifier is adopted in emotion recognition. And different feature subsets are selected in different nodes of the classifier. The highest recognition accuracy of the five emotions in Berlin database is 90.549% with only 15 features selected by RFWF. The experimental results show the effectiveness of RFWF in building feature subset and the utilization of different feature subsets for specified emotions can improve the overall recognition performance.
url http://dx.doi.org/10.1155/2017/8709518
work_keys_str_mv AT xiaoqingjiang reorderingfeatureswithweightsfusioninmulticlassandmultiplekernelspeechemotionrecognition
AT kewenxia reorderingfeatureswithweightsfusioninmulticlassandmultiplekernelspeechemotionrecognition
AT lingyinwang reorderingfeatureswithweightsfusioninmulticlassandmultiplekernelspeechemotionrecognition
AT yonglianglin reorderingfeatureswithweightsfusioninmulticlassandmultiplekernelspeechemotionrecognition
_version_ 1721332336622043136

Similar Items