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

Abstract

The detection of cry sounds is generally an important pre-processing step for various applications involving cry analysis such as diagnostic systems, electronic monitoring systems, emotion detection, and robotics for baby caregivers. Given its complexity, an automatic cry segmentation system is a rather challenging topic. In this paper, a framework for automatic cry sound segmentation for application in a cry-based diagnostic system has been proposed. The contribution of various additional time- and frequency-domain features to increase the robustness of a Gaussian mixture model/hidden Markov model (GMM/HMM)-based cry segmentation system in noisy environments is studied. A fully automated segmentation algorithm to extract cry sound components, namely, audible expiration and inspiration, is introduced and is grounded on two approaches: statistical analysis based on GMMs or HMMs classifiers and a post-processing method based on intensity, zero crossing rate, and fundamental frequency feature extraction. The main focus of this paper is to extend the systems developed in previous works to include a post-processing stage with a set of corrective and enhancing tools to improve the classification performance. This full approach allows to precisely determine the start and end points of the expiratory and inspiratory components of a cry signal, EXP and INSV, respectively, in any given sound signal. Experimental results have indicated the effectiveness of the proposed solution. EXP and INSV detection rates of approximately 94.29% and 92.16%, respectively, were achieved by applying a tenfold cross-validation technique to avoid over-fitting.

Comparative Spectrographic Analysis of the Newborns’ Cry in the Presence of Tight Intrapartum Nuchal Cord vs. Normal Using the Neonat App. Preliminary Results

“…The accuracy rates for classification tasks between healthy infants and infants with asphyxia were reported to be 93.16-94%, respectively. Moreover, anger, pain, and fear detection from cry signals were carried out, yielding a recognition rate of 90.4% [2]. The facts support our choice of data mining techniques and verify the distribution of registered cries into the aforementioned two categories.…”

“…The NBs cry has been the object of research and analysis for many years. Researchers found numerous variables that sustain the fact that cry signals can provide relevant information about the physical and psychological states of the NB [1,2].…”

Convolutional Neural Networks for Audio-Based Continuous Infant Cry Monitoring at Home

“…Although the feasibility of audio-based infant cry detection has been investigated, there are still limitations. For instance, data used in those previous studies were either recorded in a controlled environment with a fixed microphone placement [6], manually selected with a good balance between cry and non-cry sounds [8], [10], or having relatively short recordings [9], [11]. Algorithms developed on such data are likely impractical for long-term home monitoring with the presence of other baby voices (such as moaning or whining, coughing, and laughing) and various sounds (caused by, e.g., human talking, music, and car engine), as well as with different microphone placements depending on the layout of the baby room and the own preference.…”

Auditory Filterbank Learning Using ConvRBM for Infant Cry Classification

“…The classification of full-term and preterm infant cry is presented in [12]. 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].…”