Introducing new feature set based on wavelets for speech emotion classification

Roy Tanmoy; Chakraverty Snehashish; Marwala Tshilidzi; Satyakama Paul

doi:10.1109/ASPCON.2018.8748666

Introducing new feature set based on wavelets for speech emotion classification

Roy Tanmoy, Chakraverty Snehashish, Marwala Tshilidzi, Satyakama Paul

Faculty of Engineering and the Built Environment

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

Feature extraction for Speech Emotion Recognition (SER) is a challenging task and there is no consensus among researchers on a single set of features which works best. Different speech features such as pitch, energy, formants, Mel-Scale Coefficients, Predictive Coding are used for classification but results are still not satisfactory enough. In this article, a new feature set is proposed which uses Discrete Wavelet Transform (DWT) to decompose the speech signal and computes dissimilarity with the neutral emotional state. The new feature set is used for emotion classification using three different classification techniques to establish that the feature set is giving better or competitive results compared to the contemporary features.

Original language	English
Title of host publication	Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018
Editors	Sovan Dalai, Debangshu Dey, Biswendu Chatterjee, Susanta Ray
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	124-128
Number of pages	5
ISBN (Electronic)	9781538666869
DOIs	https://doi.org/10.1109/ASPCON.2018.8748666
Publication status	Published - Dec 2018
Event	2018 IEEE Applied Signal Processing Conference, ASPCON 2018 - Kolkata, India Duration: 7 Dec 2018 → 9 Dec 2018

Publication series

Name	Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018

Conference

Conference	2018 IEEE Applied Signal Processing Conference, ASPCON 2018
Country/Territory	India
City	Kolkata
Period	7/12/18 → 9/12/18

Keywords

Discrete Wavelet Transform
Feature Extraction
Machine Learning
Pattern Recognition
Signal Processing
Speech Emotion Recognition

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Instrumentation

Access to Document

10.1109/ASPCON.2018.8748666

Cite this

Tanmoy, R., Snehashish, C., Tshilidzi, M., & Paul, S. (2018). Introducing new feature set based on wavelets for speech emotion classification. In S. Dalai, D. Dey, B. Chatterjee, & S. Ray (Eds.), Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018 (pp. 124-128). Article 8748666 (Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASPCON.2018.8748666

Tanmoy, Roy ; Snehashish, Chakraverty ; Tshilidzi, Marwala et al. / Introducing new feature set based on wavelets for speech emotion classification. Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018. editor / Sovan Dalai ; Debangshu Dey ; Biswendu Chatterjee ; Susanta Ray. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 124-128 (Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018).

@inproceedings{b7c3268247ef40ff93cc5bb9c8a8a85f,

title = "Introducing new feature set based on wavelets for speech emotion classification",

abstract = "Feature extraction for Speech Emotion Recognition (SER) is a challenging task and there is no consensus among researchers on a single set of features which works best. Different speech features such as pitch, energy, formants, Mel-Scale Coefficients, Predictive Coding are used for classification but results are still not satisfactory enough. In this article, a new feature set is proposed which uses Discrete Wavelet Transform (DWT) to decompose the speech signal and computes dissimilarity with the neutral emotional state. The new feature set is used for emotion classification using three different classification techniques to establish that the feature set is giving better or competitive results compared to the contemporary features.",

keywords = "Discrete Wavelet Transform, Feature Extraction, Machine Learning, Pattern Recognition, Signal Processing, Speech Emotion Recognition",

author = "Roy Tanmoy and Chakraverty Snehashish and Marwala Tshilidzi and Satyakama Paul",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE Applied Signal Processing Conference, ASPCON 2018 ; Conference date: 07-12-2018 Through 09-12-2018",

year = "2018",

month = dec,

doi = "10.1109/ASPCON.2018.8748666",

language = "English",

series = "Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "124--128",

editor = "Sovan Dalai and Debangshu Dey and Biswendu Chatterjee and Susanta Ray",

booktitle = "Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018",

address = "United States",

}

Tanmoy, R, Snehashish, C, Tshilidzi, M & Paul, S 2018, Introducing new feature set based on wavelets for speech emotion classification. in S Dalai, D Dey, B Chatterjee & S Ray (eds), Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018., 8748666, Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018, Institute of Electrical and Electronics Engineers Inc., pp. 124-128, 2018 IEEE Applied Signal Processing Conference, ASPCON 2018, Kolkata, India, 7/12/18. https://doi.org/10.1109/ASPCON.2018.8748666

Introducing new feature set based on wavelets for speech emotion classification. / Tanmoy, Roy; Snehashish, Chakraverty; Tshilidzi, Marwala et al.
Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018. ed. / Sovan Dalai; Debangshu Dey; Biswendu Chatterjee; Susanta Ray. Institute of Electrical and Electronics Engineers Inc., 2018. p. 124-128 8748666 (Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Introducing new feature set based on wavelets for speech emotion classification

AU - Tanmoy, Roy

AU - Snehashish, Chakraverty

AU - Tshilidzi, Marwala

AU - Paul, Satyakama

PY - 2018/12

Y1 - 2018/12

N2 - Feature extraction for Speech Emotion Recognition (SER) is a challenging task and there is no consensus among researchers on a single set of features which works best. Different speech features such as pitch, energy, formants, Mel-Scale Coefficients, Predictive Coding are used for classification but results are still not satisfactory enough. In this article, a new feature set is proposed which uses Discrete Wavelet Transform (DWT) to decompose the speech signal and computes dissimilarity with the neutral emotional state. The new feature set is used for emotion classification using three different classification techniques to establish that the feature set is giving better or competitive results compared to the contemporary features.

AB - Feature extraction for Speech Emotion Recognition (SER) is a challenging task and there is no consensus among researchers on a single set of features which works best. Different speech features such as pitch, energy, formants, Mel-Scale Coefficients, Predictive Coding are used for classification but results are still not satisfactory enough. In this article, a new feature set is proposed which uses Discrete Wavelet Transform (DWT) to decompose the speech signal and computes dissimilarity with the neutral emotional state. The new feature set is used for emotion classification using three different classification techniques to establish that the feature set is giving better or competitive results compared to the contemporary features.

KW - Discrete Wavelet Transform

KW - Feature Extraction

KW - Machine Learning

KW - Pattern Recognition

KW - Signal Processing

KW - Speech Emotion Recognition

UR - http://www.scopus.com/inward/record.url?scp=85069209572&partnerID=8YFLogxK

U2 - 10.1109/ASPCON.2018.8748666

DO - 10.1109/ASPCON.2018.8748666

M3 - Conference contribution

AN - SCOPUS:85069209572

T3 - Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018

SP - 124

EP - 128

BT - Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018

A2 - Dalai, Sovan

A2 - Dey, Debangshu

A2 - Chatterjee, Biswendu

A2 - Ray, Susanta

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE Applied Signal Processing Conference, ASPCON 2018

Y2 - 7 December 2018 through 9 December 2018

ER -

Tanmoy R, Snehashish C, Tshilidzi M, Paul S. Introducing new feature set based on wavelets for speech emotion classification. In Dalai S, Dey D, Chatterjee B, Ray S, editors, Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 124-128. 8748666. (Proceedings of 2018 IEEE Applied Signal Processing Conference, ASPCON 2018). doi: 10.1109/ASPCON.2018.8748666

Introducing new feature set based on wavelets for speech emotion classification

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this