Applying an Automatic Classifier for Child-Directed Speech to Intervention Research: A Reanalysis

IF 3.2 1区心理学 Q2 PSYCHOLOGY, DEVELOPMENTAL

Developmental Science Pub Date : 2025-10-13 DOI:10.1111/desc.70079

Naja Ferjan Ramírez, Aeddan Claflin

{"title":"Applying an Automatic Classifier for Child-Directed Speech to Intervention Research: A Reanalysis","authors":"Naja Ferjan Ramírez, Aeddan Claflin","doi":"10.1111/desc.70079","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <p>Parental language input is a key predictor of child language achievement. Parentese is a widely used style of child-directed speech (CDS) distinguished by a higher pitch and larger pitch range. A recent parent coaching randomized control trial (Parentese-RCT) demonstrated that English-speaking US parents who were coached to use parentese with their 6- to 18-month-olds increased the frequency of its use; their children showed enhanced language outcomes at 18 months. While these results are exciting, a roadblock in scaling this intervention is the fact that parentese has to be manually identified from daylong LENA recordings. Here we demonstrate that a newly developed CDS classifier captures the effect of this Parentese-RCT <i>without human annotation</i>, through a new variable: Proportion of CDS relative to all adult speech (CDS-Proportion). Two daylong recordings per child (<i>N</i> = 70) per timepoint (child age: 6, 10, 14, and 18 months) from the Parentese-RCT were re-analyzed by removing periods of sleep and estimating CDS-Proportion through the classifier. As was the case for parentese in the Parentese-RCT, CDS-Proportion was significantly enhanced in the intervention group. Moreover, the change over time in CDS-Proportion was significantly and positively correlated with infants’ word use at 18 months. We emphasize that the classifier does <i>not</i> “recognize parentese.” Likewise, CDS-Proportion is <i>not</i> a proxy for parentese, but rather, a variable related to parentese in complex ways. The present findings suggest a promising future for scalability of interventions using daylong recordings in combination with novel technologies.</p>\n </section>\n \n <section>\n \n <h3> Summary</h3>\n \n <div>\n <ul>\n \n <li>Language interventions promote verbal engagement between caregivers and children; however, to be effective, these interventions need to be scalable.</li>\n \n <li>Language interventions have relied on manual (human) annotation to identify parental language behaviors that are linked to children's outcomes.</li>\n \n <li>An automated classifier for Child-Directed-Speech was applied to capture the effect of a previously published parent-coaching intervention, without human annotation.</li>\n \n <li>Novel technologies have the potential to enhance the scalability of parent interventions that focus on social language behaviors.</li>\n </ul>\n </div>\n </section>\n </div>","PeriodicalId":48392,"journal":{"name":"Developmental Science","volume":"28 6","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Developmental Science","FirstCategoryId":"102","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/desc.70079","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHOLOGY, DEVELOPMENTAL","Score":null,"Total":0}

引用次数: 0

Abstract

Parental language input is a key predictor of child language achievement. Parentese is a widely used style of child-directed speech (CDS) distinguished by a higher pitch and larger pitch range. A recent parent coaching randomized control trial (Parentese-RCT) demonstrated that English-speaking US parents who were coached to use parentese with their 6- to 18-month-olds increased the frequency of its use; their children showed enhanced language outcomes at 18 months. While these results are exciting, a roadblock in scaling this intervention is the fact that parentese has to be manually identified from daylong LENA recordings. Here we demonstrate that a newly developed CDS classifier captures the effect of this Parentese-RCT without human annotation, through a new variable: Proportion of CDS relative to all adult speech (CDS-Proportion). Two daylong recordings per child (N = 70) per timepoint (child age: 6, 10, 14, and 18 months) from the Parentese-RCT were re-analyzed by removing periods of sleep and estimating CDS-Proportion through the classifier. As was the case for parentese in the Parentese-RCT, CDS-Proportion was significantly enhanced in the intervention group. Moreover, the change over time in CDS-Proportion was significantly and positively correlated with infants’ word use at 18 months. We emphasize that the classifier does not “recognize parentese.” Likewise, CDS-Proportion is not a proxy for parentese, but rather, a variable related to parentese in complex ways. The present findings suggest a promising future for scalability of interventions using daylong recordings in combination with novel technologies.

Summary

Language interventions promote verbal engagement between caregivers and children; however, to be effective, these interventions need to be scalable.
Language interventions have relied on manual (human) annotation to identify parental language behaviors that are linked to children's outcomes.
An automated classifier for Child-Directed-Speech was applied to capture the effect of a previously published parent-coaching intervention, without human annotation.
Novel technologies have the potential to enhance the scalability of parent interventions that focus on social language behaviors.

Abstract Image

查看原文本刊更多论文

儿童导向言语自动分类器在干预研究中的应用。

父母的语言输入是儿童语言成就的关键预测因素。父母语是一种广泛使用的儿童导向语，其特点是音调较高，音域较大。最近的一项父母训练随机对照试验（parentesrct）表明，说英语的美国父母在与6至18个月大的孩子一起使用父母语时，使用频率增加了；他们的孩子在18个月大时表现出更强的语言能力。虽然这些结果令人兴奋，但扩大这种干预措施的一个障碍是，必须从全天的LENA记录中手动识别父母语。在这里，我们展示了一个新开发的CDS分类器，通过一个新的变量：CDS相对于所有成人言语的比例（CDS-Proportion），捕获了这种没有人工注释的parentes_rct的效果。每个时间点（儿童年龄：6个月、10个月、14个月和18个月）每个儿童（N = 70）的2天记录来自parentes - rct，通过删除睡眠时间和通过分类器估计CDS-Proportion重新分析。与parentese - rct中parentese的情况一样，干预组的CDS-Proportion显著提高。此外，随着时间的推移，cds -比例的变化与婴儿在18个月时的单词使用显著正相关。我们强调分类器不“识别父母语”。同样，CDS-Proportion也不是parentese的代理，而是一个以复杂方式与parentese相关的变量。目前的研究结果表明，使用全天记录与新技术相结合的干预措施的可扩展性具有广阔的前景。总结：语言干预促进了照顾者和儿童之间的语言交流；然而，要想有效，这些干预措施必须具有可扩展性。语言干预依赖于手工（人类）注释来识别与儿童结果相关的父母语言行为。一个儿童导向语言的自动分类器被应用于捕捉先前发表的父母指导干预的效果，而不需要人工注释。新技术有可能提高关注社会语言行为的父母干预的可扩展性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Developmental Science Multiple-

CiteScore

8.10

自引率

8.10%

发文量

132

期刊介绍： Developmental Science publishes cutting-edge theory and up-to-the-minute research on scientific developmental psychology from leading thinkers in the field. It is currently the only journal that specifically focuses on human developmental cognitive neuroscience. Coverage includes: - Clinical, computational and comparative approaches to development - Key advances in cognitive and social development - Developmental cognitive neuroscience - Functional neuroimaging of the developing brain