• Mrs. Vimlesh Vishwakarma
• Mr. Rajneesh Pachouri
• Mr. Anurag Jain

Infant cries serve as a vital communication mechanism, conveying essential needs such as hunger, discomfort, or pain. Accurately interpreting these cries can significantly aid caregivers and medical professionals in ensuring the well-being of infants. This study presents CryML Classifier, a machine learning-based system designed to classify baby cries into five categories: burping, belly pain, discomfort, hungry, and tired. The system utilizes advanced acoustic feature extraction techniques, including 40 Mel-Frequency Cepstral Coefficients (MFCCs), 12 chroma features, 128 mel-spectrogram features, 7 spectral contrast features, and 6 tonnetz features, yielding a comprehensive set of 193 features per sample. The classification task was performed using various machine learning algorithms, such as K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Trees, Random Forest, and XGBoost. Among these, Random Forest and XGBoost demonstrated exceptional accuracy, achieving approximately 99.59% and 99.79% respectively on the Donate a Cry Corpus Dataset. A detailed comparative analysis highlights the strengths and limitations of these models in handling the intricacies of infant cry signals. This research underscores the importance of robust feature extraction and model selection for developing reliable cry classification systems, paving the way for advancements in healthcare and infant monitoring

Baby Cry Classification, Machine Learning, Acoustic Feature Extraction, Random Forest, XGBoost, Infant Cry Analysis

"Classification of Baby Cries Using Advanced Machine Learning Algorithms: A Comparative Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 9, page no.f185-f190, September-2025, Available :http://www.jetir.org/papers/JETIR2509526.pdf

"Classification of Baby Cries Using Advanced Machine Learning Algorithms: A Comparative Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 9, page no. ppf185-f190, September-2025, Available at : http://www.jetir.org/papers/JETIR2509526.pdf