Anger detection in Arabic speech dialogs

Ashraf Khalil, Wasfi Al-Khatib, El-Sayed El-Alfy, Lahouari Cheded

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Anger is potentially the most important human emotion to be detected in human-human dialogs, such as those found in call-centers and other similar fields. It directly measures the level of satisfaction of a speaker from his or her voice. Recently, many software applications were built as a result of the anger detection research work. In this paper, we design a framework to detect anger from spontaneous Arabic conversations. We construct a well-Annotated corpus for anger and neutral emotion states from real-world Arabic speech dialogs for our experiments. The classification is based on acoustic sound features that are more appropriate for anger detection. Many acoustic features will be explored such as the fundamental frequency, formants, energy and Mel-frequency cepstral coefficients (MFCCs). Several classifiers are evaluated, and the experimental results show that support vector machine classifiers can yield more than 77% real-Time anger detection rate.

Original languageEnglish
Title of host publication2018 International Conference on Computing Sciences and Engineering, ICCSE 2018 - Proceedings
EditorsHazem Raafat, Mostafa Abd-El-Barr, Muhammad Sarfraz, Paul Manuel
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
ISBN (Electronic)9781538646809
DOIs
StatePublished - 5 Jun 2018
Event2nd International Conference on Computing Sciences and Engineering, ICCSE 2018 - Kuwait City, Kuwait
Duration: 11 Mar 201813 Mar 2018

Publication series

Name2018 International Conference on Computing Sciences and Engineering, ICCSE 2018 - Proceedings

Conference

Conference2nd International Conference on Computing Sciences and Engineering, ICCSE 2018
Country/TerritoryKuwait
CityKuwait City
Period11/03/1813/03/18

Fingerprint

Dive into the research topics of 'Anger detection in Arabic speech dialogs'. Together they form a unique fingerprint.

Cite this