A Classification Model for Infant Cries with Hearing Impairment and Unilateral Cleft Lip and Palate

Abstract

Objective: The aim of the study was to examine the acoustic features of infant cries in order to find differences between infants with normal development, hearing impairment (HI) and unilateral cleft lip and palate (UCLP). The study focused on two issues: (1) are differences in acoustic cry parameters specific of a certain pathological development, and (2) do these differences allow for a reliable classification of infant cries? Patients and Methods: In total, 128 spontaneous cries of infants up to 12 months of age were recorded. The mean values of acoustic cry parameters were statistically analyzed by one-way analysis of variance and Sheffé post hoc tests. A C5.0 decision tree was trained to classify infant cries by their acoustic parameters. Results: Significant differences in cry duration, fundamental frequency, formants 2 and 4, intensity, jitter, shimmer and harmonics-to-noise ratio were found between the groups. The C5.0 decision tree was able to predict an infant’s membership to the healthy, UCLP or HI groups with a probability of 89.2%. Conclusion: We conclude that C5.0 decision trees are suited to reliably classify healthy infants as well as infants with HI and UCLP by acoustic parameters.

Acoustic Analysis of Crying Signal in Infants with Disabling Hearing Impairment

“…The fundamental frequency is vibration of the vocal folds. 20 Hamzavi et al, 21 Wermke et al, 15 and Etz et al 12 showed the mean F 0 is greater in HI individuals than NH individuals. Varallyay and Beny o et al 22 reported the same results.…”

“…Vocalization in infants up to 12 months of age has been shown to be dependent on auditory feedback. 11,12 But on the one hand, unlike crying, vocalization such as cooing and babbling does not exist in the first days of birth and it is crucial to detect the hearing impairment in the first days of birth, and on the other hand, there are contradictory opinions about the difference in vocalization between the two groups. As a result, we will study the differences in crying between the two groups in this study.…”

Are Cry Studies Replicable? An Analysis of Participants, Procedures, and Methods Adopted and Reported in Studies of Infant Cries

“…Specific differences in cry features are associated with different pathologies. For example, a higher fundamental frequency in cry utterances is associated with a higher risk of autism spectrum disorder diagnosis [30,[38][39][40], while hearing-impaired infants produce longer vocalizations with lower second formant (F 2 ) and less energy in the higher frequency bands [41,42]. Knowledge about the health status of investigated infants is necessary to correctly evaluate the obtained results.…”

Are Cry Studies Replicable? An Analysis of Participants, Setups, and Methods Adopted and Reported in Cry Studies

“…Specific differences in cry features are associated with different pathologies. For example, a higher fundamental frequency in cry utterances is associated with a higher risk of autism spectrum disorder diagnosis [27,[35][36][37], while hearing-impaired infants produce longer vocalizations with lower second formant (F 2 ) and less energy in the higher frequency bands [38,39]. Knowledge about the health status of investigated infants is necessary to correctly evaluate the obtained results.…”