Aggression in Hindi and English Speech: Acoustic Correlates and Automatic Identification
This work addresses the need for automated aggression detection in speech for applications like content moderation, though it is incremental as it applies existing acoustic modeling methods to new languages and data.
The study tackled the problem of identifying aggression in Hindi and English speech by analyzing acoustic features in political discourse, resulting in automatic classifiers achieving accuracies of over 73% for Hindi and 66% for English.
In the present paper, we will present the results of an acoustic analysis of political discourse in Hindi and discuss some of the conventionalised acoustic features of aggressive speech regularly employed by the speakers of Hindi and English. The study is based on a corpus of slightly over 10 hours of political discourse and includes debates on news channel and political speeches. Using this study, we develop two automatic classification systems for identifying aggression in English and Hindi speech, based solely on an acoustic model. The Hindi classifier, trained using 50 hours of annotated speech, and English classifier, trained using 40 hours of annotated speech, achieve a respectable accuracy of over 73% and 66% respectively. In this paper, we discuss the development of this annotated dataset, the experiments for developing the classifier and discuss the errors that it makes.