Analysis of acoustic features of infant cry for classification purposes

The infant´s cry is a vocal signal that was proven to be a way of communication that aims to get the attention of the listener to a given physical state like hunger or pain. This work deals with the analysis of the acoustic features of the infant cry offering a starting point for the development of an automatic classification system. Standard features such as pitch and intensity were analyzed. A sample-based and a sequence-based studies were carried out in order to discover special properties of the infant cry. The preliminary results delivered helpful information about acoustic statistics and correlation between cry features.