AUDD: Audio Urdu Digits Dataset for Automatic Audio Urdu Digit Recognition

The ongoing development of audio datasets for numerous languages has spurred research activities towards designing smart speech recognition systems. A typical system can be applied in many emerging applications, such as smartphone dialing, airline reservations, and automatic wheelchairs, among others. Urdu is a national language Pakistan also widely spoken other South Asian countries (e.g., India, Afghanistan). Therefore, we present comprehensive dataset digits ranging from 0 to 9. Our 25,518 sound samples that are collected 740 participants. To test the proposed dataset, apply different existing classification algorithms on including Support Vector Machine (SVM), Multilayer Perceptron (MLP), flavors EfficientNet. These serve baseline. Furthermore, propose convolutional neural network (CNN) digit classification. We conduct experiment using these networks, results show CNN efficient outperforms baseline terms accuracy.