“…Some Arabic speeches emotion datasets have been proposed in the literature, see [1]- [3], [5], [19]. Each dataset has a different set of classes or labels, for example, the Arabic audio acted dataset proposed in [20] has five labels (Happiness, Sadness, Neutral, Anger, Fear), and the dataset proposed in [15] has three classes (Happy, Surprised, and Angry), while the dataset proposed in [19] has labels (Happy, Sad, Neutral, Angry, Surprise, Disgust).…”