Feature extraction and recognition of infant cries

This paper utilizes signal boundary detection and linear predictive coding coefficients (LPCC) in order to analyze and extract features from infant cry instances such that the causes of the cry can be recognized. Consistent reference signals for three separate cry pathologies (hunger, wet diaper, and a need for attention) were decomposed to generate training vectors for cry recognition. Qualitative matching was defined on the basis of similarity between unknown cry LPCC to the weighted coefficients of each of the three training vectors. The experiments show that the analysis of LPCC was a feasible method of recognizing infant cries in order to improve infant care devices.