A review: survey on automatic infant cry analysis and classification (original) (raw)
Related papers
A review of infant cry analysis and classification
EURASIP Journal on Audio, Speech, and Music Processing, 2021
This paper reviews recent research works in infant cry signal analysis and classification tasks. A broad range of literatures are reviewed mainly from the aspects of data acquisition, cross domain signal processing techniques, and machine learning classification methods. We introduce pre-processing approaches and describe a diversity of features such as MFCC, spectrogram, and fundamental frequency, etc. Both acoustic features and prosodic features extracted from different domains can discriminate frame-based signals from one another and can be used to train machine learning classifiers. Together with traditional machine learning classifiers such as KNN, SVM, and GMM, newly developed neural network architectures such as CNN and RNN are applied in infant cry research. We present some significant experimental results on pathological cry identification, cry reason classification, and cry sound detection with some typical databases. This survey systematically studies the previous researc...
On the implementation of a method for automatic detection of infant cry units
Procedia Engineering, 2012
In Infant Cry Analysis, the cry units are the most important parts of the cry wave to be analyzed. The cry units are segments of cry in the recorded samples the separation of these segments from the rest of the recording is known as cry units detection. Currently, the detection of cry units is done by expert doctors, who perform the detection based on their visual and auditory perception, which is done by inspecting spectrograms and listening the recorded samples. Here, a method based on the energy of the signal measure is presented, which allows to automatically detect, in an effective way the cry units from a recording, even under noise conditions. In this paper we describe the implemented method as well as some encouraging results.
Biomedical Signal Processing and Control
In the infant cry analysis, the identification of qualitative features is of great importance, because this provides relevant information to differentiate between normal and pathological cries, which makes important their identification. Qualitative infant cry analysis has been done until now by medical personal through visual inspection of spectrograms and by the auditory study of the cry recordings. In this way, the success of the process depends on the subjective perception of the inspector besides being a very slow task. The information extracted from the perceptive observation of the crying waves recordings is then used as a help to emit diagnosis. With the idea of helping to make the whole process easier and faster we are developing a method to automatically identify, measure and highlight selected qualitative features in infant cry recordings. The processing of this identifier starts with the automatic discovery of infant cry units, which is performed by the use of a threshold applied to the energy of the signal along with another threshold applied to eliminate inspiratory cry segments, when not needed. From all the detected cry units, the process automatically identifies melodic shape, shifts, glides and noise concentration. In this work, we present, besides a quick review of related works, and a description of the perceptive analysis to help diagnosis, the process implementation, some experiments as well as the experimental results obtained.
Infant Screening System Based on Cry Analysis
2018
Acoustical investigation of infant cries has been a clinical and research focus in the recent years. Findings of several studies reveal the importance of cry as a useful window for early detection of several diseases and communication difficulties such as hearing impairment, intellectual disabilities, cerebral palsy etc. This motivates us to use a minimal interface system that can automatically classify infant cries into normal and pathological with the help of state-of-the-art machine learning strategies. In this paper, we propose a software program for screening infants based on their cries. The proposed system is able to detect & classify infant cries into normal and pathological based on the acoustic input. To build and train the system, infant cries of normal and Low Birth Weight (LBW) newborn within 7 days of birth were considered. A pain induced cry elicited using the routine intramuscular immunization was recorded using a standard Olympus LS-100 recorder which was held about...
Newborn's pathological cry identification system
2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), 2012
In this paper we compare the performance of an identification system of the pathological and normal cries of the newborn, using various methods of characterisation of cries. This system is similar to a speaker identification system. It contains two main parts namely a cry signal characterisation and modeling. We used Mel-Frequency Cestrum Coefficients and Mel Frequency Discret Wavelet Coefficients to characterize the newborn cry signals. We also applied Best Structure Abstract Tree algorithm and the Principal Component Analysis to reduce the number of Wavelet packet transform WPT coefficients. In this study a Probabilistic Neural Network classifier is used. The best result obtained is 96.
Statistical Vectors of Acoustic Features for the Automatic Classification of Infant Cry
International Journal of Information Acquisition, 2007
With the objective of helping diagnose some pathologies in recently born babies, we present the experiments and results obtained in the classification of infant cry using a variety of single classifiers, and ensembles from the combination of them. Three kinds of cry were classified: normal, hypoacoustic (deaf), and asphyxia. The feature vectors were formed by the extraction of Mel Frequency Cepstral Coefficients (MFCC). The vectors were then processed and reduced through the application of five statistics operations, namely: minimum, maximum, average, standard deviation and variance. LDA, a data reduction technique is implemented with the purpose of comparing the results of our proposed method. Four supervised machine learning methods including Support Vector Machines, Neural Networks, J48, Random Forest and Naive Bayes are used. The ensembles tested were combinations of these under different approaches like Majority Vote, Staking, Bagging and Boosting.
Automatic infant cry analysis and recognition
1993
In presenting this thesis in partial fulfilment of the requirements for an advanced degree at the University of British Columbia, I agree that the Library shall make it freely available for reference and study. I further agree that permission for extensive copying of this thesis for scholarly purposes may be granted by the head of my department or by his or her representatives. It is understood that copying or publication of this thesis for financial gain shall not be allowed without my written permission.
Analysis of Cry in New Born Infants
IJARCCE, 2015
The acoustic analysis of infant cry is used to deduce information on the state of health of newborn babies as well as of children a few weeks old. Crying is the first tool of communication for an infant. These cries seem to be uniform, but there are a lot of differences between two infant"s cries. Infant cry characteristics reflect the development and possibly the integrity of the central nervous system. The preterm infants and infants with neurological conditions have different cry characteristics like fundamental frequency, when compared to healthy full term infant. There are differences between full term and preterm infant in their neuro-physiological maturity and its impact on their speech development. Cry characteristics of New born infant, changes with increase in age. Acoustics analysis of infant cry signals can thus give an aid to clinical diagnosis and prevention of distress since it is easy to perform, cheap and completely non-invasive. Hence, this paper aims at pre-processing to eliminate silenced region of cry signal and estimating the fundamental frequency (pitch) using time domain and frequency domain analysis. Such parameters are of interest in exploring brain function at early stages of child development, for the timely diagnosis of neonatal disease and malformation.