FCM-based multiple random forest for speech emotion recognition

Mengtian Zhou; Luefeng Chen; Jianping Xu; Xianghui Cheng; Min Wu; Weihua Cao; Jinhua She; Kaoru Hirota

FCM-based multiple random forest for speech emotion recognition

Mengtian Zhou, Luefeng Chen^*, Jianping Xu, Xianghui Cheng, Min Wu, Weihua Cao, Jinhua She, Kaoru Hirota

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

3 Citations (Scopus)

Abstract

Speech emotion recognition (SER) is of great importance in the human-robot interaction, and SER have been developed rapidly in recent years. How to identify high correlation features is a main question. In this paper, multiple random forest (MRF) is proposed, which can effectively predict up to several thousand explanatory variables, and improve the recognition result. At the mean time, personalized features and non-personalized features are fused for SER that can be divided into different subclasses by adopting the fuzzy C-means (FCM) clustering algorithm, then FCM-based MRF is proposed. Finally, our model is established, and the confusion matrix is output. Moreover, we conduct a separate classification of some certain emotion, which are difficult to recognition to some extent. And results show that the proposed method of FCM-based MRF achieves good performance for SER, which the recognition accuracy is 84.17%.

Original language	English
Publication status	Published - 2017
Externally published	Yes
Event	5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017 - Beijing, China Duration: 2 Nov 2017 → 5 Nov 2017

Conference

Conference	5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017
Country/Territory	China
City	Beijing
Period	2/11/17 → 5/11/17

Keywords

Fuzzy C-means
Non-personalized feature
Random forest
Speech emotion recognition

Cite this

@conference{55b59aa85357456099c20f61abb024e7,

title = "FCM-based multiple random forest for speech emotion recognition",

abstract = "Speech emotion recognition (SER) is of great importance in the human-robot interaction, and SER have been developed rapidly in recent years. How to identify high correlation features is a main question. In this paper, multiple random forest (MRF) is proposed, which can effectively predict up to several thousand explanatory variables, and improve the recognition result. At the mean time, personalized features and non-personalized features are fused for SER that can be divided into different subclasses by adopting the fuzzy C-means (FCM) clustering algorithm, then FCM-based MRF is proposed. Finally, our model is established, and the confusion matrix is output. Moreover, we conduct a separate classification of some certain emotion, which are difficult to recognition to some extent. And results show that the proposed method of FCM-based MRF achieves good performance for SER, which the recognition accuracy is 84.17%.",

keywords = "Fuzzy C-means, Non-personalized feature, Random forest, Speech emotion recognition",

author = "Mengtian Zhou and Luefeng Chen and Jianping Xu and Xianghui Cheng and Min Wu and Weihua Cao and Jinhua She and Kaoru Hirota",

year = "2017",

language = "English",

note = "5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017 ; Conference date: 02-11-2017 Through 05-11-2017",

}

TY - CONF

T1 - FCM-based multiple random forest for speech emotion recognition

AU - Zhou, Mengtian

AU - Chen, Luefeng

AU - Xu, Jianping

AU - Cheng, Xianghui

AU - Wu, Min

AU - Cao, Weihua

AU - She, Jinhua

AU - Hirota, Kaoru

PY - 2017

Y1 - 2017

N2 - Speech emotion recognition (SER) is of great importance in the human-robot interaction, and SER have been developed rapidly in recent years. How to identify high correlation features is a main question. In this paper, multiple random forest (MRF) is proposed, which can effectively predict up to several thousand explanatory variables, and improve the recognition result. At the mean time, personalized features and non-personalized features are fused for SER that can be divided into different subclasses by adopting the fuzzy C-means (FCM) clustering algorithm, then FCM-based MRF is proposed. Finally, our model is established, and the confusion matrix is output. Moreover, we conduct a separate classification of some certain emotion, which are difficult to recognition to some extent. And results show that the proposed method of FCM-based MRF achieves good performance for SER, which the recognition accuracy is 84.17%.

AB - Speech emotion recognition (SER) is of great importance in the human-robot interaction, and SER have been developed rapidly in recent years. How to identify high correlation features is a main question. In this paper, multiple random forest (MRF) is proposed, which can effectively predict up to several thousand explanatory variables, and improve the recognition result. At the mean time, personalized features and non-personalized features are fused for SER that can be divided into different subclasses by adopting the fuzzy C-means (FCM) clustering algorithm, then FCM-based MRF is proposed. Finally, our model is established, and the confusion matrix is output. Moreover, we conduct a separate classification of some certain emotion, which are difficult to recognition to some extent. And results show that the proposed method of FCM-based MRF achieves good performance for SER, which the recognition accuracy is 84.17%.

KW - Fuzzy C-means

KW - Non-personalized feature

KW - Random forest

KW - Speech emotion recognition

UR - http://www.scopus.com/inward/record.url?scp=85037538237&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85037538237

T2 - 5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017

Y2 - 2 November 2017 through 5 November 2017

ER -

FCM-based multiple random forest for speech emotion recognition

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this