On the use of MFCC and SWT-based features for offensive speech detection in social media
Safa Chebbi, Sara Sekkate, Sofia Ben Jebara, Abdellah Adib · 2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA) · 2021
Research on psychological comfort and serenity in social media becomes a necessity because of the excess of negative waves generated by the users. In this paper, we aim to distinguish between offensive and ordinary speech based on machine learning classification techniques. For this purpose, the VAM emotional audio database has been restructured and adjusted to the context of offensive speech detection. Besides, a feature fusion based on Mel Frequency Cepstral Coefficients (MFCCs) as well as Stationary Wavelet Transform (SWT) has been employed and K-nearest neighbors (KNN) algorithm has been used as a classification tool. Results show that the considered feature set has relatively great power in recognizing suspicious behavior, reaching 96.2% as the highest accuracy rate.