Validation of the Cry Unit as Primary Element for Cry Analysis Using an Evolutionary-Neural Approach

The present paper proposes the use of a basic element for the infant cry analysis: the Cry Unit. In order to display the real possibility of the cry unit for the detection of pathological features (based on Hypoxia) in newborns, a novel combined treatment of the cry signal was implemented using an evolutionary-neural system. For that purpose the cry signal was segmented into cry units, the MFCC were computed as acoustic features, and a genetic feature selection system combined with a feed forward input delay neural network, trained by adaptive learning rate back-propagation were properly developed. The data for the experiments were obtained from a Mexican-Cuban infant cry database. It is also shown a comparison between a simple neural network and the proposed genetic feature selection system, to reduce the feature input vectors. The results are also shown from some experiments, in which the infant cry recognition is improved to 100% using our genetic system.