Emotional speech classification in consensus building

Ning He, Shuoqing Yao, Osamu Yoshie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we introduce a novel approach that robust automatic speech features recognition of one's emotion is achieved in a classification model named decision forest. The 13th order of Mel-frequency ceptstrum coefficients (MFCC) vector is processed as the multivariate data that will be imported to our classifier. In order to draw underlying and inductive information behind the MFCC feature, our decision forest classifier contains two stages to make classification, a supervised clustering based pattern extraction stage and a soft discretization based decision forest stage. Finally, a Japanese emotion corpus used for training and evaluation is described in detail. The results in recognition of six discrete emotions exceeded a mean value of 81% recognition rate.

Original languageEnglish
Title of host publicationIEEE International Conference on Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479923854
DOIs
Publication statusPublished - 2014
Event2014 10th International Conference on Communications, COMM 2014 - Bucharest
Duration: 2014 May 292014 May 31

Other

Other2014 10th International Conference on Communications, COMM 2014
CityBucharest
Period14/5/2914/5/31

Fingerprint

Classifiers

Keywords

  • classification
  • consensus building
  • decision forest
  • MFCC
  • speech emotion recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Cite this

He, N., Yao, S., & Yoshie, O. (2014). Emotional speech classification in consensus building. In IEEE International Conference on Communications [6866670] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICComm.2014.6866670

Emotional speech classification in consensus building. / He, Ning; Yao, Shuoqing; Yoshie, Osamu.

IEEE International Conference on Communications. Institute of Electrical and Electronics Engineers Inc., 2014. 6866670.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

He, N, Yao, S & Yoshie, O 2014, Emotional speech classification in consensus building. in IEEE International Conference on Communications., 6866670, Institute of Electrical and Electronics Engineers Inc., 2014 10th International Conference on Communications, COMM 2014, Bucharest, 14/5/29. https://doi.org/10.1109/ICComm.2014.6866670
He N, Yao S, Yoshie O. Emotional speech classification in consensus building. In IEEE International Conference on Communications. Institute of Electrical and Electronics Engineers Inc. 2014. 6866670 https://doi.org/10.1109/ICComm.2014.6866670
He, Ning ; Yao, Shuoqing ; Yoshie, Osamu. / Emotional speech classification in consensus building. IEEE International Conference on Communications. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{ff5a5f65525b44329e5f355f753b3d77,
title = "Emotional speech classification in consensus building",
abstract = "In this paper we introduce a novel approach that robust automatic speech features recognition of one's emotion is achieved in a classification model named decision forest. The 13th order of Mel-frequency ceptstrum coefficients (MFCC) vector is processed as the multivariate data that will be imported to our classifier. In order to draw underlying and inductive information behind the MFCC feature, our decision forest classifier contains two stages to make classification, a supervised clustering based pattern extraction stage and a soft discretization based decision forest stage. Finally, a Japanese emotion corpus used for training and evaluation is described in detail. The results in recognition of six discrete emotions exceeded a mean value of 81{\%} recognition rate.",
keywords = "classification, consensus building, decision forest, MFCC, speech emotion recognition",
author = "Ning He and Shuoqing Yao and Osamu Yoshie",
year = "2014",
doi = "10.1109/ICComm.2014.6866670",
language = "English",
isbn = "9781479923854",
booktitle = "IEEE International Conference on Communications",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Emotional speech classification in consensus building

AU - He, Ning

AU - Yao, Shuoqing

AU - Yoshie, Osamu

PY - 2014

Y1 - 2014

N2 - In this paper we introduce a novel approach that robust automatic speech features recognition of one's emotion is achieved in a classification model named decision forest. The 13th order of Mel-frequency ceptstrum coefficients (MFCC) vector is processed as the multivariate data that will be imported to our classifier. In order to draw underlying and inductive information behind the MFCC feature, our decision forest classifier contains two stages to make classification, a supervised clustering based pattern extraction stage and a soft discretization based decision forest stage. Finally, a Japanese emotion corpus used for training and evaluation is described in detail. The results in recognition of six discrete emotions exceeded a mean value of 81% recognition rate.

AB - In this paper we introduce a novel approach that robust automatic speech features recognition of one's emotion is achieved in a classification model named decision forest. The 13th order of Mel-frequency ceptstrum coefficients (MFCC) vector is processed as the multivariate data that will be imported to our classifier. In order to draw underlying and inductive information behind the MFCC feature, our decision forest classifier contains two stages to make classification, a supervised clustering based pattern extraction stage and a soft discretization based decision forest stage. Finally, a Japanese emotion corpus used for training and evaluation is described in detail. The results in recognition of six discrete emotions exceeded a mean value of 81% recognition rate.

KW - classification

KW - consensus building

KW - decision forest

KW - MFCC

KW - speech emotion recognition

UR - http://www.scopus.com/inward/record.url?scp=84907379528&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907379528&partnerID=8YFLogxK

U2 - 10.1109/ICComm.2014.6866670

DO - 10.1109/ICComm.2014.6866670

M3 - Conference contribution

AN - SCOPUS:84907379528

SN - 9781479923854

BT - IEEE International Conference on Communications

PB - Institute of Electrical and Electronics Engineers Inc.

ER -