An Efficient Classification of Neonates Cry Using Extreme Gradient Boosting-Assisted Grouped-Support-Vector Network

The cry is a loud, high pitched verbal communication of infants. The very high fundamental frequency and resonance frequency characterize a neonatal infant cry having certain sudden variations. Furthermore, in a tiny duration solitary utterance, the cry signal also possesses both voiced and unvoiced features. Mostly, infants communicate with their caretakers through cries, and sometimes, it becomes difficult for the caretakers to comprehend the reason behind the newborn infant cry. As a result, this research proposes a novel work for classifying the newborn infant cries under three groups such as hunger, sleep, and discomfort. For each crying frame, twelve features get extracted through acoustic feature engineering, and the variable selection using random forests was used for selecting the highly discriminative features among the twelve time and frequency domain features. Subsequently, the extreme gradient boosting-powered grouped-support-vector network is deployed for neonate cry classification. The empirical results show that the proposed method could effectively classify the neonate cries under three different groups. The finest experimental results showed a mean accuracy of around 91% for most scenarios, and this exhibits the potential of the proposed extreme gradient boosting-powered grouped-support-vector network in neonate cry classification. Also, the proposed method has a fast recognition rate of 27 seconds in the identification of these emotional cries.

An fNIRS Investigation of Masculinity, Femininity and Sex on Nonparents’ Empathic Response to Infant Cries

According to societal stereotypes, the female sex and people who are more feminine have been considered to be more empathic than males and people who are more masculine. Therefore, females and feminine individuals are expected to respond more empathically to an infant’s cries. While this hypothesis was tested using self-report scales, it has not been explored thoroughly in terms of prefrontal cortex (PFC) activity, which may be a more objective means of measuring empathy. Specifically, the medial PFC (mPFC) is involved in social cognitive processing and thus a good proxy to measure the level of empathy. This study aims to (1) assess if the empathic response, in terms of medial PFC (mPFC) activity, to infant cries differ between sexes; (2) investigate if the empathic response is moderated by levels of masculinity and femininity. Functional near-infrared spectroscopy (fNIRS) was used to measure nonparent participants’ (18 males, 20 females) mPFC response to infant cries of different pitches (high and low). The Toronto Empathy Questionnaire was used to measure trait empathy and Bem’s Sex Role Inventory was used to measure the level of masculinity and femininity. Results revealed that biological sex had no significant effect on the empathic response towards infant cries of varying pitch. Furthermore, masculinity, not femininity, was correlated with an increase in empathic response in the mPFC to high but not low-pitch infant cries. We reason that this is because of the higher aversiveness and inflicted pain associated with higher-pitched cries, which induces more emotional and physical pain that masculine individuals seek to avoid. Overall, the results suggest that greater masculinity would imply greater mentalizing and processing of empathy-related information.

Neural circuitry for maternal oxytocin release induced by infant cries

SummaryOxytocin is a neuropeptide important for maternal physiology and childcare, including parturition and milk ejection during nursing. Suckling triggers oxytocin release, but other sensory cues- specifically infant cries- can elevate oxytocin levels in new human mothers, indicating that cries can activate hypothalamic oxytocin neurons. Here we describe a neural circuit routing auditory information about infant vocalizations to the oxytocin system of the mouse brain. We performed in vivo electrophysiological recordings and photometry from identified oxytocin neurons in awake maternal mice presented with pup calls. We found that oxytocin neurons responded to pup vocalizations via input from the posterior intralaminar thalamus, and repetitive thalamic stimulation induced lasting disinhibition of oxytocin neurons. Suppression of this pathway impaired maternal behavior and playing pup calls led to central oxytocin release in vivo. This circuit provides a mechanism for transforming acoustic input into hormonal output to ensure modulation of brain state required for successful parenting.

Innate sensitivity and plastic mechanisms in auditory cortex for reliable maternal behavior

Infant cries evoke powerful responses in parents1–4. To what extent are parental animals innately sensitive to neonatal vocalizations, or might instead learn about key vocal cues for appropriate parenting responses? In mice, naive virgins do not recognize the meaning of pup distress calls, but begin to retrieve pups to the nest following cohousing with a mother and litter5–8. These isolation calls can be variable, requiring co-caring virgins to generalize across features for reliable retrieval9, 10. Here, using behavioral studies combined with two-photon imaging and whole-cell recordings, we show that the onset of maternal behavior in mice results from the interaction between innate sensitivities and experience-dependent processes. We found that pup calls with inter-syllable intervals (ISIs) ranging from 75 to 375 ms elicited pup retrieval, and experienced auditory cortex generalized across these ISIs. In contrast, naive cortex was narrowly tuned to the most common or ‘prototypical’ ISIs due to enhanced short-term depression of inhibitory inputs. Behavioral testing revealed that naive virgins were also more sensitive to prototypical calls than calls at other rates. Inhibitory and excitatory spiking and synaptic responses were initially mismatched in naive cortex, with untuned inhibition and overly-narrow excitation. Monitoring neuronal populations over cohousing revealed that excitatory neuronal responses broadened to represent a wide range of ISIs, while inhibitory neurons sharpened to form a perceptual boundary. Finally, we presented synthetic calls during cohousing and observed that neural and behavioral responses adjusted to match these statistics. Using inhibitory optogenetics, we found that auditory cortical activity was required to learn about specific features, whereas the oxytocinergic system was generally recruited for retrieval learning and plasticity in temporal tuning. Neuroplastic mechanisms therefore build on an innate sensitivity in the auditory cortex, enabling rapid plasticity for reliable parenting behavior.

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

Infant cry is evolutionarily, psychologically, and clinically significant. Over the last half century, several researchers and clinicians have investigated acoustical properties of infant cry for medical purposes. However, this literature suffers a lack of standardization in conducting and reporting cry-based studies. In this work, methodologies and procedures employed to analyze infant cry are reviewed and best practices for reporting studies are provided. First, available literatures on vocal and audio acoustic analysis are examined to identify critical aspects of participant information, data collection, methods, and data analysis. Then, 180 peer-reviewed research articles have been assessed to certify the presence of critical information. Results show a general lack of critical description. Researchers in the field of infant cry need to develop a consensual standard set of criteria to report experimental studies to ensure the validity of their methods and results.

Comparison of Supervised-Learning Models and Auditory Discrimination of Infant Cries for the Early Detection of Developmental Disorders / Vergleich von Supervised-Learning Klassifikationsmodellen und menschlicher auditiver Diskriminationsfähigkeit zur Unterscheidung von Säuglingsschreien mit kongenitalen Entwicklungsstörungen

Infant cry classification can be performed in two ways: computational classification of cries or auditory discrimination by human listeners. This article compares both approaches. An auditory listening experiment was performed to examine if various listener groups (naive listeners, parents, nurses/midwives and therapists) were able to distinguish auditorily between healthy and pathological cries as well as to differentiate various pathologies from each other. Listeners were trained in hearing cries of healthy infants and cries of infants suffering from cleft-lip-and-palate, hearing impairment, laryngomalacia, asphyxia and brain damage. After training, a listening experiment was performed by allocating 18 infant cries to the cry groups. Multiple supervised-learning classifications models were calculated on the base of the cries’ acoustic properties. The accuracy of the models was compared to the accuracy of the human listeners. With a Kappa value of 0.491, listeners allocated the cries to the healthy and the five pathological groups with moderate performance. With a sensitivity of 0.64 and a specificity of 0.89, listeners were able to identify that a cry is a pathological one with higher confidence than separating between the single pathologies. Generalized linear mixed models found no significant differences between the classification accuracy of the listener groups. Significant differences between the pathological cry types were found. Supervised-learning classification models performed significantly better than the human listeners in classifying infant cries. The models reached an overall Kappa value of up to 0.837.

neural responses to infant vocalizations in adult listeners

Infant vocalizations are uniquely salient sounds in our auditory environment. They attract attention and compel the listener to respond quickly and carefully. These sounds prompt a range of effortful and complex behaviours in parents, with the goal of providing life-sustaining care for their infant. The neurobiological underpinnings of this motivational state are of much interest to auditory and parenting researchers alike. Neuroimaging has afforded the opportunity to examine the biological substrates of these complex states. Functional MRI (fMRI) studies have identified a network of cortical and subcortical regions that are reactive to infant cries. This ‘parental brain’ is a combination of regions of the ‘social brain’ (temporal and frontal lobe areas) and subcortical ‘survival’ regions. Temporally sensitive neuroimaging techniques (magnetoencephalography, MEG and local field potentials, LFPs) are beginning to illuminate the dynamic nature of activity among these regions, with findings demonstrating early (50–200 ms) identification of infant cries in the periaqueductal grey and orbitofrontal cortex that may support rapid orientating responses. Emerging work investigating parental experience-dependent brain plasticity suggests associations between various aspects of parenting behaviour and adaptations in fronto-amygdala circuitry. Future work combining levels of analyses in longitudinal designs may lead to a better understanding of caregiving behaviour in health and disease.