Normal Infant Cry Research Articles

Significance of Higher-Order Spectral Analysis in Infant Cry Classification

In this paper, higher-order spectral analysis is applied to infant cry signals for classification of normal infant cries from pathological infant cries. From the family of higher-order spectra, bispectrum is considered for the proposed task. Bispectrum is the Fourier transform of the third-order cumulant function. To extract features from the bispectrum, application of higher-order singular value decomposition theorem is proposed. Experimental results show the average classification accuracy of \({82.44} \pm {4.03}{ \%}\) and Matthew’s correlation coefficient (MCC) of 0.62 with proposed bispectrum features. In all of the experiments reported in this paper, support vector machine with radial basis function kernel is used as the pattern classifier. Performance of the proposed features is also compared with the state-of-the-art methods such as linear frequency cepstral coefficients, Mel frequency cepstral coefficients, perceptual linear prediction coefficients, linear prediction coefficients, linear prediction cepstral coefficients and perceptual linear prediction cepstral coefficients, and is found to be better than that given by these feature sets. The proposed bispectrum-based features are shown to be robust under signal degradation or noisy conditions at various SNR levels. Performance in the presence of noise is compared with the state-of-the-art spectral feature sets using MCC scores. In addition, effectiveness of cryunit segmentation in normal and pathological infant cry classification task is reported.

The acoustic characteristics of the cry of an infant with unilateral vocal fold paralysis

We have previously shown the acoustic similarity among well, full-term infants of the same post-conceptional and post-partum ages (Int. J. Pediat. Otorhinolaryngol., 10 (1985) 1–8). The objective of that research was to provide a template against which the cries of any given infant may be compared. This paper shows a more detailed analysis of both the normal infants' cries and the cry of an infant with a unilateral vocal fold paralysis. It is evident from this analysis that this infant's cry is not normal as it displays a spectrum not found in the cries of normal infants. What this research shows is that a technique is available with which it is possible to make a screening identification of those infants who merit further investigation. It is an objective of such research to determine if the cry of a given infant is abnormal in specifiable, and therefore diagnostic, ways. In this instance, we can conclude that the cry of this infant differs from that of one with a normal airway.

Fathers' and mothers' responses to the faces and cries of normal and premature infants.

Sixty-four parents were shown videotapes depicting infants who were, in turn, quiescent, crying, and quiescent. Half of the parents viewed a normal (full term) newborn, while half viewed a premature infant. Sound tracks were dubbed so that half of the normal and half of the premature infants ' 'emitted the cry of a normal infant, while the other half emitted the cry of a premature infant. Physiological and self-report measures were gathered. Analyses revealed that the cry of the premature infant elicited greater autonomic arousal and was perceived as more aversive than the cry of the normal infant. The effect was especially pronounced when the premature cry was paired with the face of a premature infant. There were few sex differences. Results are discussed with reference to demographic evidence indicating that prematurely born children are at risk for child abuse.

The phonetic content of the cries of normal infants and those with brain damage.

The phonetic content of the cries of normal infants and those with brain damage.

Frequency spectra of the cries of normal infants and those with Down’s Syndrome

Samples of tape recorded crying obtained from four male mongoloid infants six months of age, and four normal infants matched for age and sex were fed into the Panoramic Sonic Analyzer in order to survey the frequency (c. p. s.) content of the cries. While the frequency ranges did not differ for the two groups, the cries of the normal infants were richer in spectral content, more active, less variable in sound level and more homogeneous as a group than those of the mongoloid infants.