Why is My Baby Crying? An In-Depth Analysis of Paralinguistic Features and Classical Machine Learning Algorithms for Baby Cry Classification

摘要

As human beings, we begin interacting with the world by expressing our basic needs through crying. Parents strive to identify and timely address these needs before hysterical crying sets in. However, first-time parents usually fail, and this leads to frustration and feelings of helplessness. In this context, our work focuses on creating an automatic system able to distinguish between different infant needs based on crying. We extract various sets of paralinguistic features from the baby-cry audio signals and we train various rule-based or statistical classifiers. We evaluate and in-depth compare the results and obtain up to 70% accuracy on the evaluation dataset.