• Dr. S.M. Ali
• Samiksha Nagpure
• Ruqaiya Anjum
• Mubasshira Ali

This paper present an infant emotion recognition system using audio information. Crying or making sound is not just an infant behaviour but a part of human system that assures survival.There are various reasons related to an infant crying such as hunger, anger ,happy, sad,cooing etc .There are many research paper have been written on analysis of infant by using various methods i.e, melody shape method, inverse filtering etc. ,In this paper we used feature extraction technique that includes power spectrum density, mean-average values, then covert it into mel-frequency which is quite simpler then other extraction methods. Back propagation neural network is used as classifier . The set of data is made from processed infant crying data ,there are two sets of data i.e, training data and testing data.GUI(Graphical user interface) is used to represent the information and make it easy to understand. In this research we study five reasons due to which the infant is crying .hopefully, in next research more reasons of crying can be added which will impact on the accuracy .

Feature extraction, Mel frequency, GUI

"INFANT SOUND BEHAVIOUR ANALYSIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.363-366, May-2019, Available :http://www.jetir.org/papers/JETIRBV06081.pdf

"INFANT SOUND BEHAVIOUR ANALYSIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp363-366, May-2019, Available at : http://www.jetir.org/papers/JETIRBV06081.pdf