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

2024/10/11 by Lee, Kyunghun, Henry, Lauren M., Hansen, Eleanor +6
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2410.09236

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.

Related

• Infant Crying Detection in Real-World Environments
• Infant Cry Detection Using Causal Temporal Representation
• Weakly Supervised Detection of Baby Cry
• Self-supervised learning for infant cry analysis
• Domain-Agnostic Causal-Aware Audio Transformer for Infant Cry Classification