Enhancing Infant Crying Detection with Gradient Boosting for Improved Emotional and Mental Health Diagnostics

TL;DR

This paper presents a novel audio analysis method combining Wav2Vec features and traditional audio features with Gradient Boosting Machines to improve infant cry detection accuracy for health diagnostics.

Contribution

It introduces an integrated approach using deep learning and traditional features with gradient boosting for enhanced infant cry classification.

Findings

Significant performance improvements over existing methods

Effective integration of Wav2Vec and traditional audio features

Validated on real-world dataset

Abstract

Infant crying can serve as a crucial indicator of various physiological and emotional states. This paper introduces a comprehensive approach detecting infant cries within audio data. We integrate Wav2Vec with traditional audio features and employ Gradient Boosting Machines for cry classification. We validate our approach on a real world dataset, demonstrating significant performance improvements over existing methods.