Validating a model to detect infant crying from naturalistic audio

Micheletti, Megan; Yao, Xuewen; Johnson, Mckensey; Barbaro, Kaya de

doi:10.3758/s13428-022-01961-x

Cited by 9 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Any nonverbal vocal expression of negative emotion, including cries, fusses, whines, and whimpers, were automatically identified by LENA as “crying” (Fields-Olivieri & Cole, 2019). As LENA's cry algorithm has been shown to underestimate crying time relative to human annotations (Micheletti et al, 2022), we compared LENA's cry output to human annotations of cry for 40% of our participants. Trained human coders annotated 24-hour recordings for n = 22 participants quasi-randomly selected to represent the age distribution of our overall sample.…”

Section: Methodsmentioning

confidence: 99%

“…In effect, we multiplied all original durations by approximately a factor of three which resulted in cry estimates that more closely approximate the gold-standard human-annotated values for each time frame. Converging evidence suggests that a correction factor should be applied to LENA crying data to compensate for its underestimation of child vocalizations (Cristia et al, 2021; Micheletti et al, 2022). This transformation is equivalent to changing from one unit to another and thus has no effect on our results.…”

Section: Methodsmentioning

confidence: 99%

“…Advances in wearable sensors, paired with algorithms that can automatically detect markers of interest, provide a relatively low-burden method for capturing large volumes of objective measures of context, including infant crying (de Barbaro, 2019; Micheletti et al, 2022). Researchers have successfully used sensors to assess objective measures of sleep, physical activity, and even geographic location as real-time predictors of mental health (Mohr et al, 2017).…”

Section: The Current Studymentioning

confidence: 99%

“…large individual differences in daily crying duration (Kurth et al, 2011;St James-Roberts & Plewis, 1996) and 5%-25% of infants are identified with colic, or excessive crying (Lucassen et al, 2001;Wolke et al, 2017). Mothers who report their infants cry excessively also report experiencing higher levels of caregiver frustration (Barr et al, 2014;Fujiwara et al, 2011) and emotional distress (Miller et al, 1993), as well as higher concurrent depression and anxiety symptoms (Petzoldt, 2018). Furthermore, mothers of infants with a temperament profile which includes high levels of irritability and crying also exhibit higher levels of depression and anxiety symptoms (Britton, 2011).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Infant crying predicts real-time fluctuations in maternal mental health in ecologically valid home settings.

Barbaro¹,

Micheletti²,

Yao³

et al. 2023

Developmental Psychology

Self Cite

View full text Add to dashboard Cite

Exposure to infant crying is a well-established predictor of mothers' mental health. However, this association may reflect many potential mechanisms. Capturing dynamic fluctuations in mothers’ states simultaneously with caregiving experiences is necessary to identify the real-time processes influencing mental health. In this study, we leveraged ecological momentary assessments (EMAs) and infant-worn audio recorders to capture variability in mothers’ mental health symptoms and their exposure to infant crying over one week in a racially and socio-economically diverse urban North-American sample (N = 53). We use multilevel modeling to characterize within- and between-person effects of crying on maternal negative affect and symptoms of depression and anxiety. Within participants, when infants cried more than average in the 10 min, 1 hr, and 8 hr prior to an EMA report, mothers’ negative affect subsequently increased, controlling for mean levels of infant crying. In contrast to findings from laboratory studies, in everyday settings crying exposure did not immediately increase feelings of depression. Only when crying was above average for 8 hr prior to EMA did mothers report increases in subsequent depression symptoms, suggesting that the effects of crying on maternal mental health take hours to unfold in ecologically valid home settings. Between participants, mothers of infants who cried more on average did not report higher negative affect or symptoms of depression or anxiety. Overall, our findings reveal that crying exposure dynamically influences maternal negative affect and depression but not anxiety in ecologically valid real-world settings.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: The Current Studymentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Infant crying predicts real-time fluctuations in maternal mental health in ecologically valid home settings.

Barbaro¹,

Micheletti²,

Yao³

et al. 2023

Developmental Psychology

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, it will be essential for future research to test whether depressed mothers and mothers of highly NA infants become less responsive to infant distress over time because they do not receive the ostensibly reinforcing signal of infant soothing when they do respond during episodes of infant distress. Mobile sensing tools to capture and automatically detect infant crying over extended periods of time, for example, hours, days, or weeks can facilitate such future work (de Barbaro, 2019; Micheletti et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Maternal contingent responses to distress facilitate infant soothing but not in mothers with depression or infants high in negative affect.

de Barbaro,

Khante,

Maier

et al. 2024

Developmental Psychology

View full text Add to dashboard Cite

Depression in mothers is consistently associated with reduced caregiving sensitivity and greater infant negative affect expression. The current article examined the real-time behavioral mechanisms underlying these associations using Granger causality time series analyses in a sample of mothers (N = 194; 86.60% White) at elevated risk for depression and their 3-month-old infants (46.40% female) living in a major metropolitan area in the United States. Overall, mothers contingently responded to infant distress, and mothers' responses to infant distress increased the likelihood of infant soothing in real time. However, there was no evidence for maternal contingent responding or facilitation of infant soothing in subsamples of mothers who were currently experiencing elevated depression symptoms or in mothers of highly negative infants. These findings suggest real-time behavioral mechanisms by which risks for maladaptive self-regulation may develop. Public Significance StatementOverall, mothers contingently respond to infant distress, and their responses to distress facilitate infant soothing. However, in groups of mothers with depression symptoms and groups of infants who show high levels of distress, we do not find evidence for such regulation behaviors. Our results suggest that both mothers and infants play key roles in infants' developing self-regulation.

show abstract

Understanding behaviours in context using mobile sensing

Harari,

Gosling

2023

Nat Rev Psychol

View full text Add to dashboard Cite

Validating a model to detect infant crying from naturalistic audio

Cited by 9 publications

References 27 publications

Infant crying predicts real-time fluctuations in maternal mental health in ecologically valid home settings.

Infant crying predicts real-time fluctuations in maternal mental health in ecologically valid home settings.

Maternal contingent responses to distress facilitate infant soothing but not in mothers with depression or infants high in negative affect.

Understanding behaviours in context using mobile sensing

Contact Info

Product

Resources

About