Spoken emotion classification using ToBI features and GMM

Alexander I. Iliev, Yongxin Zhang, Michael S Scordilis

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

8 Citations (Scopus)

Abstract

This study investigated the usefulness of ToBI marks in determining the emotional state conveyed in speech. The Gaussian Mixture Model GMM used was as the classifier structure. A total of three different classification systems were developed based on the use of three different feature vectors. They were: (a) the classical approach that used signal pitch and energy features; (b) a ToBI-only feature based on tone and break tiers; and (c) a system that used the features of both (a) and (b). In ToBI, tone tier elements were automatically determined using pitch information. Three emotional states were investigated: Happiness, Anger, and Sadness. The overall success rate achieved for the combined system was between 75% and 100%. This work indicated that the ToBI features alone were very useful for the classification of emotion, and detection improves when classical features are used in conjunction with ToBI.

Original languageEnglish
Title of host publication2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services
Pages495-498
Number of pages4
DOIs
StatePublished - Dec 1 2007
Event14th International Conference on Systems Signals and Image Processing, IWSSIP 2007 and 6th EURASIP Conference Focused on Speech and Image Processing, Multimedia Communications and Services, EC-SIPMCS 2007 - Maribor, Slovenia
Duration: Jun 27 2007Jun 30 2007

Other

Other14th International Conference on Systems Signals and Image Processing, IWSSIP 2007 and 6th EURASIP Conference Focused on Speech and Image Processing, Multimedia Communications and Services, EC-SIPMCS 2007
CountrySlovenia
CityMaribor
Period6/27/076/30/07

Fingerprint

Classifiers

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Control and Systems Engineering

Cite this

Iliev, A. I., Zhang, Y., & Scordilis, M. S. (2007). Spoken emotion classification using ToBI features and GMM. In 2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services (pp. 495-498). [4381149] https://doi.org/10.1109/IWSSIP.2007.4381149

Spoken emotion classification using ToBI features and GMM. / Iliev, Alexander I.; Zhang, Yongxin; Scordilis, Michael S.

2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services. 2007. p. 495-498 4381149.

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

Iliev, AI, Zhang, Y & Scordilis, MS 2007, Spoken emotion classification using ToBI features and GMM. in 2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services., 4381149, pp. 495-498, 14th International Conference on Systems Signals and Image Processing, IWSSIP 2007 and 6th EURASIP Conference Focused on Speech and Image Processing, Multimedia Communications and Services, EC-SIPMCS 2007, Maribor, Slovenia, 6/27/07. https://doi.org/10.1109/IWSSIP.2007.4381149
Iliev AI, Zhang Y, Scordilis MS. Spoken emotion classification using ToBI features and GMM. In 2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services. 2007. p. 495-498. 4381149 https://doi.org/10.1109/IWSSIP.2007.4381149
Iliev, Alexander I. ; Zhang, Yongxin ; Scordilis, Michael S. / Spoken emotion classification using ToBI features and GMM. 2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services. 2007. pp. 495-498
@inproceedings{f73d9f041aa64661999d54e77e3e5836,
title = "Spoken emotion classification using ToBI features and GMM",
abstract = "This study investigated the usefulness of ToBI marks in determining the emotional state conveyed in speech. The Gaussian Mixture Model GMM used was as the classifier structure. A total of three different classification systems were developed based on the use of three different feature vectors. They were: (a) the classical approach that used signal pitch and energy features; (b) a ToBI-only feature based on tone and break tiers; and (c) a system that used the features of both (a) and (b). In ToBI, tone tier elements were automatically determined using pitch information. Three emotional states were investigated: Happiness, Anger, and Sadness. The overall success rate achieved for the combined system was between 75{\%} and 100{\%}. This work indicated that the ToBI features alone were very useful for the classification of emotion, and detection improves when classical features are used in conjunction with ToBI.",
author = "Iliev, {Alexander I.} and Yongxin Zhang and Scordilis, {Michael S}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IWSSIP.2007.4381149",
language = "English",
isbn = "9789612480295",
pages = "495--498",
booktitle = "2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services",

}

TY - GEN

T1 - Spoken emotion classification using ToBI features and GMM

AU - Iliev, Alexander I.

AU - Zhang, Yongxin

AU - Scordilis, Michael S

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This study investigated the usefulness of ToBI marks in determining the emotional state conveyed in speech. The Gaussian Mixture Model GMM used was as the classifier structure. A total of three different classification systems were developed based on the use of three different feature vectors. They were: (a) the classical approach that used signal pitch and energy features; (b) a ToBI-only feature based on tone and break tiers; and (c) a system that used the features of both (a) and (b). In ToBI, tone tier elements were automatically determined using pitch information. Three emotional states were investigated: Happiness, Anger, and Sadness. The overall success rate achieved for the combined system was between 75% and 100%. This work indicated that the ToBI features alone were very useful for the classification of emotion, and detection improves when classical features are used in conjunction with ToBI.

AB - This study investigated the usefulness of ToBI marks in determining the emotional state conveyed in speech. The Gaussian Mixture Model GMM used was as the classifier structure. A total of three different classification systems were developed based on the use of three different feature vectors. They were: (a) the classical approach that used signal pitch and energy features; (b) a ToBI-only feature based on tone and break tiers; and (c) a system that used the features of both (a) and (b). In ToBI, tone tier elements were automatically determined using pitch information. Three emotional states were investigated: Happiness, Anger, and Sadness. The overall success rate achieved for the combined system was between 75% and 100%. This work indicated that the ToBI features alone were very useful for the classification of emotion, and detection improves when classical features are used in conjunction with ToBI.

UR - http://www.scopus.com/inward/record.url?scp=48049117743&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48049117743&partnerID=8YFLogxK

U2 - 10.1109/IWSSIP.2007.4381149

DO - 10.1109/IWSSIP.2007.4381149

M3 - Conference contribution

AN - SCOPUS:48049117743

SN - 9789612480295

SP - 495

EP - 498

BT - 2007 IWSSIP and EC-SIPMCS - Proc. 2007 14th Int. Workshop on Systems, Signals and Image Processing, and 6th EURASIP Conf. Focused on Speech and Image Processing, Multimedia Communications and Services

ER -