Classification of infant cries using epoch and spectral features

Abstract

In this paper, epoch and spectral features are explored for classifying infant cries. Different types of infant cries considered in this work are hunger, pain and wet-diaper. In this work, mel-frequency cepstral coefficients (MFCC), epoch interval contour (EIC) features are used for representing the infant cry specific information from the acoustic signal. The information contributed by the excitation source is different compared to vocal tract system. Excitation source specific features such as Epoch interval contour obtained from Zero Frequency Filtering(ZFF) method is explored in this work in addition to system based features. Gaussian Mixture Models (GMM) are used for classifying the above mentioned cries from the features proposed in this work. GMM models are developed separately by using the proposed features. Infant cry database collected under telemedicine project at IIT-KGP has been used for carrying out this study. For enhancing the recognition performance, GMM models developed using various features are combined using feature and score level fusion techniques. The recognition performance using combination of evidences is found to be superior over individual systems.