Published Paper Details:

This review paper explores recent advancements in infant cry analysis using artificial intelligence (AI) methodologies, particularly machine learning (ML) and deep learning (DL). The discussion consolidates findings from ten notable studies focusing on techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and support vector machines (SVMs), with key acoustic features including Mel-Frequency Cepstral Coefficients (MFCCs). Results indicate that enhanced DL methods significantly improve detection accuracy in challenging environments like neonatal intensive care units (NICUs). Challenges remain, such as dataset limitations, non-uniform labelling standards, and the need for real-time applications. This paper provides a synthesized perspective on current methodologies and outlines future directions for creating intelligent cry interpretation systems to support early healthcare interventions [1]-[10].