A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM

A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM

Feature extraction is a very important part in speech emotion recognition, and in allusion to feature extraction in speech emotion recognition problems, this paper proposed a new method of feature extraction, using DBNs in DNN to extract emotional features in speech signal automatically. By training...

Full description

Bibliographic Details
Main Authors: Chenchen Huang, Wei Gong, Wenlong Fu, Dongyu Feng
Format: Article
Language:English
Published: Hindawi Limited 2014-01-01
Series:Mathematical Problems in Engineering
Online Access:http://dx.doi.org/10.1155/2014/749604
id doaj-07ed29dbf7a64dc48197fbb987663fbb
record_format Article
spelling doaj-07ed29dbf7a64dc48197fbb987663fbb2020-11-24T23:47:49ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472014-01-01201410.1155/2014/749604749604A Research of Speech Emotion Recognition Based on Deep Belief Network and SVMChenchen Huang0Wei Gong1Wenlong Fu2Dongyu Feng3Department of Computer, Communication University of China, Beijing 100024, ChinaDepartment of Computer, Communication University of China, Beijing 100024, ChinaDepartment of Computer, Communication University of China, Beijing 100024, ChinaDepartment of Computer, Communication University of China, Beijing 100024, ChinaFeature extraction is a very important part in speech emotion recognition, and in allusion to feature extraction in speech emotion recognition problems, this paper proposed a new method of feature extraction, using DBNs in DNN to extract emotional features in speech signal automatically. By training a 5 layers depth DBNs, to extract speech emotion feature and incorporate multiple consecutive frames to form a high dimensional feature. The features after training in DBNs were the input of nonlinear SVM classifier, and finally speech emotion recognition multiple classifier system was achieved. The speech emotion recognition rate of the system reached 86.5%, which was 7% higher than the original method.http://dx.doi.org/10.1155/2014/749604
collection DOAJ
language English
format Article
sources DOAJ
author Chenchen Huang
Wei Gong
Wenlong Fu
Dongyu Feng
spellingShingle Chenchen Huang
Wei Gong
Wenlong Fu
Dongyu Feng
A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM
Mathematical Problems in Engineering
author_facet Chenchen Huang
Wei Gong
Wenlong Fu
Dongyu Feng
author_sort Chenchen Huang
title A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM
title_short A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM
title_full A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM
title_fullStr A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM
title_full_unstemmed A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM
title_sort research of speech emotion recognition based on deep belief network and svm
publisher Hindawi Limited
series Mathematical Problems in Engineering
issn 1024-123X
1563-5147
publishDate 2014-01-01
description Feature extraction is a very important part in speech emotion recognition, and in allusion to feature extraction in speech emotion recognition problems, this paper proposed a new method of feature extraction, using DBNs in DNN to extract emotional features in speech signal automatically. By training a 5 layers depth DBNs, to extract speech emotion feature and incorporate multiple consecutive frames to form a high dimensional feature. The features after training in DBNs were the input of nonlinear SVM classifier, and finally speech emotion recognition multiple classifier system was achieved. The speech emotion recognition rate of the system reached 86.5%, which was 7% higher than the original method.
url http://dx.doi.org/10.1155/2014/749604
work_keys_str_mv AT chenchenhuang aresearchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
AT weigong aresearchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
AT wenlongfu aresearchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
AT dongyufeng aresearchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
AT chenchenhuang researchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
AT weigong researchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
AT wenlongfu researchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
AT dongyufeng researchofspeechemotionrecognitionbasedondeepbeliefnetworkandsvm
_version_ 1725488465414455296

Similar Items