Anger Detection in Arabic Speech Dialogs

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.