Paper Title
Infant Cry Analysis for Emotion Detection by using Feature Extraction Methods

Abstract
Crying is not just an infant behavior, but a part of behavioral system in human that assures survival of the helpless neonate by eliciting others to meet basic needs. It is a way of communication for the infant and a positive sign of a healthy life. Various reasons are responsible for an infant’s cry that includes hungry, unhappy, discomfort, sadness, stomach pain, hascolic or any other diseased conditions. An infant’s cry cannot be just taken as common manners of neonates but a serious response of its conditions. Thus the analysis of infant cry effectively identifies the state of health of new born babies. Many research papers have been written on the analysis of infants by using various methods i.e., spectography, melody shape method, inverse filtering etc., In this paper we used a different method to detect the emotion of crying infant. Feature extraction techniques that include Mel-frequency and Linear predictive coding methods have been used. GUI (Graphical User Interface) is used to study and analyze the reason. A statistical tool is used to compare the efficiency of the two techniques (Mel-frequency and linear predictive coding). In the present work the study is performed for five reasons due to which the infant is crying: hascolic, hungry, sad, stomach pain, unhappy. Keywords - Feature extraction, GUI, Infant cry, Statistics.