Mt-USAE Dataset

The Multi-tone Urdu Speech Audio Emotion (Mt-USAE) dataset was developed using a group of 20 speakers. This group contains a 50:50 ratio of male and female participants. The age of each participant was between 20 to 40 years. The diversity in age and gender demographics reflects the typical linguistic variations within the Urdu-speaking population. The selection criteria ensured a balanced representation in terms of age, gender, and regional accents to capture the rich emotional expression characteristics.