Automatic Recognition of Baby Crying Sounds

This paper suggests the use of deep learning techniques for the automatic classification of infant cry sounds. The primary aim of the proposed study is to automatically determine infants’ basic needs by analyzing their cry sounds in real-time. To achieve this goal, deep learning techniques were employed for the sensitive and effective classification of infant cry sounds. Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) models utilized in the study were evaluated using accuracy and F1 score metrics. The experimental results indicate that the proposed method is more effective compared to previous studies on the same dataset. Specifically, it was observed that data augmentation and segmentation techniques applied in various scenarios for the classification of infant cry sounds enhanced the model’s performance. The proposed study demonstrates the potential usefulness of employing deep learning techniques in the automatic analysis of infant cry sounds.