Expiratory and Inspiratory Cries Detection Using Different Signals' Decomposition Techniques

Abstract

This paper addresses the problem of automatic cry signal segmentation for the purposes of infant cry analysis. The main goal is to automatically detect expiratory and inspiratory phases from recorded cry signals. The approach used in this paper is made up of three stages: signal decomposition, features extraction, and classification. In the first stage, short-time Fourier transform, empirical mode decomposition (EMD), and wavelet packet transform have been considered. In the second stage, various set of features have been extracted, and in the third stage, two supervised learning methods, Gaussian mixture models and hidden Markov models, with four and five states, have been discussed as well. The main goal of this work is to investigate the EMD performance and to compare it with the other standard decomposition techniques. A combination of two and three intrinsic mode functions (IMFs) that resulted from EMD has been used to represent cry signal. The performance of nine different segmentation systems has been evaluated. The experiments for each system have been repeated several times with different training and testing datasets, randomly chosen using a 10-fold cross-validation procedure. The lowest global classification error rates of around 8.9% and 11.06% have been achieved using a Gaussian mixture models classifier and a hidden Markov models classifier, respectively. Among all IMF combinations, the winner combination is IMF3+IMF4+IMF5.

A fully automated approach for baby cry signal segmentation and boundary detection of expiratory and inspiratory episodes

“…Based on the results obtained from our previous works (Abou-Abbas et al , 2017; Abou-Abbas et al , 2015c) regarding finding the best IMF combination, we have found that the parameters extracted from the sum of IMF3, IMF4, and IMF5 yielded the best cry segmentation results. Therefore, this combination was employed in this work: IMF345 = IMF3 + IMF4 + IMF5.…”

“…Our database in this work consists of a total of 507 waveforms of cry sounds interspersed by different unwanted acoustic activities. A summary of the database is given in Tables II and III, and it is the same database as used in our previous work (Abou-Abbas et al , 2017) for comparison purposes.…”

“…In the works conducted previously (Abou-Abbas et al , 2017; Abou-Abbas et al , 2015b; Abou-Abbas et al , 2015c), studies were carried out to compare the accuracy rate of different feature vectors and classifiers. It has been shown that all of the proposed approaches mentioned in Table V allow for reliable discrimination of clean expiration from any other sounds.…”

Auditory Filterbank Learning Using ConvRBM for Infant Cry Classification

“…Recently, an automatic cry segmentation system is proposed as a pre-processing step in the infant cry classification task [13]. Other notable studies for infant cry classification include the works reported in [14][15][16][17][18][19][20][21]. The detailed discussion on the topic of infant cry classification is found in [7] and in [22], the first Ph.D. thesis from India in this area.…”

Identification of diseases in newborns using advanced acoustic features of cry signals

“…Flowchart of adopted approach.In the first step, cry signals were processed manually using PRAAT (a freeware program for the analysis and reconstruction of acoustic speech signals)[29]. The automated preprocessing method is currently being investigated by other researchers studying the PICS[30]. Because the recorded sounds include the background noises, speech, sound of medical equipment, and silence, some of these parts may distort the results of the analysis.…”