Identification of hearing disorder by multi-band entropy cepstrum extraction from infant's cry

Infant's cry is a multimodal behavior that contains a lot of information about the infant, particularly, information about the health of the infant. In this paper a new feature in infant cry analysis is presented for recognition two groups: infants with hearing disorder and normal infants, by Mel frequency multi-band entropy cepstrum extraction from infant's cry. Signal processing stage is included by silence elimination, filtering, pre-emphasizing and feature extraction. After taking Fourier transform, spectral entropy was computed as single feature for all of cry sample. In classifying stage, by training artificial neural network, correction rate of recognition was obtained 73.6%. In order to enhancement in results, we used Mel filter bank. Entropy of each sub-band constitutes elements of next feature vector. By applying Discrete Cosine Transform (DCT) over logarithm of this vector, new feature vector were obtained, we named them MFECs. By MFECs vectors we achieved 88.3% of correction rate. So, MFECs are convenient features to classify cry of infants with hearing disorder from normal infants.