{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:30:35Z","timestamp":1786494635641,"version":"build-2736575974"},"reference-count":29,"publisher":"The Royal Society","issue":"8","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea government","award":["RS-2023-00251378"],"award-info":[{"award-number":["RS-2023-00251378"]}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education of the Republic of Korea","doi-asserted-by":"publisher","award":["NRF-2026S1A5A8010250"],"award-info":[{"award-number":["NRF-2026S1A5A8010250"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002471","name":"Dongguk University Research Fund","doi-asserted-by":"publisher","award":["S-2025-G0001-00139"],"award-info":[{"award-number":["S-2025-G0001-00139"]}],"id":[{"id":"10.13039\/501100002471","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>As speech-based artificial intelligence (AI) becomes integrated into educational contexts, attention is growing towards its role in supporting child-centred learning environments. This study offers insights for developing child-friendly conversational AI systems by analysing age-specific linguistic and acoustic features in the speech of Korean-speaking children aged 4\u20139 years. The study was conducted in three phases: linguistic analysis of transcribed text, acoustic analysis of recorded utterances and automatic speech recognition (ASR) analysis. In the ASR phase, we benchmarked two modern models (Whisper and wav2vec2) using character error rate and performed a classification analysis to identify factors influencing recognition success, excluding age-related variables from model inputs. The results revealed age-related differences in vocabulary diversity, syntactic complexity, pitch, intensity and articulation rate, with younger children exhibiting more frequent pronunciation errors and lower ASR performance. Acoustic features, such as articulation patterns and pitch variability, were found to significantly influence recognition performance. These findings highlight the importance of designing AI systems that reflect children's developmental speech characteristics. Overall, this study provides an empirical foundation for improving speech-based AI interactions in early learning environments.<\/jats:p>","DOI":"10.1098\/rsos.252306","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:15:03Z","timestamp":1786493703000},"source":"Crossref","is-referenced-by-count":0,"title":["Analysing Korean children's speech data for early childhood educational services: age-specific insights from text and audio analysis"],"prefix":"10.1098","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9718-6395","authenticated-orcid":false,"given":"Haein","family":"Lee","sequence":"first","affiliation":[{"name":"School of Interdisciplinary Studies, Dongguk University 1 , Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8634-7212","authenticated-orcid":false,"given":"Hae Sun","family":"Jung","sequence":"additional","affiliation":[{"name":"Division of Artificial Intelligence and Data Science, Korea Cyber University 2 , Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4100-2585","authenticated-orcid":false,"given":"Keon Chul","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Business Administration, Tech University of Korea 3 , Siheung-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"175","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"2026081120143178000_RSOS252306C1","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/1529100615569721","article-title":"Putting education in \u2018educational\u2019 apps: lessons from the science of learning","volume":"16","author":"Hirsh-Pasek","year":"2015","journal-title":"Psychol. Sci. Public Interest"},{"key":"2026081120143178000_RSOS252306C2","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1111\/j.1467-8535.2012.01323.x","article-title":"Pre-school children creating and communicating with digital technologies in the home","volume":"44","author":"McPake","year":"2013","journal-title":"Br. J. Educ. Technol."},{"key":"2026081120143178000_RSOS252306C3","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1111\/tops.12192","article-title":"Young children treat robots as informants","volume":"8","author":"Breazeal","year":"2016","journal-title":"Top. Cogn. Sci."},{"key":"2026081120143178000_RSOS252306C4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0002-7138(09)62273-1","article-title":"The infant's response to entrapment between contradictory messages in face-to-face interaction","volume":"17","author":"Tronick","year":"1978","journal-title":"J. Am. Acad. Child Psychiatry"},{"key":"2026081120143178000_RSOS252306C5","doi-asserted-by":"crossref","DOI":"10.1787\/589b283f-en","article-title":"Social robots as educators","volume-title":"OECD digital education outlook 2021 pushing the frontiers with artificial intelligence, blockchain and robots: pushing the frontiers with artificial intelligence, blockchain and robots","author":"Belpaeme","year":"2021"},{"key":"2026081120143178000_RSOS252306C6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-30033-3_27","article-title":"Employing a voice-based emotion-recognition function in a social chatbot to foster social and emotional learning among preschoolers","volume-title":"Int. Conf. Human-Computer Interaction","author":"Tsai","year":"2019"},{"key":"2026081120143178000_RSOS252306C7","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.compedu.2013.10.003","article-title":"Children's engagement with educational iPad apps: insights from a Spanish classroom","volume":"71","author":"Kucirkova","year":"2014","journal-title":"Comput. Educ."},{"key":"2026081120143178000_RSOS252306C8","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.compedu.2014.09.006","article-title":"A contextual game-based learning approach to improving students' inquiry-based learning performance in social studies courses","volume":"81","author":"Hwang","year":"2015","journal-title":"Comput. Educ."},{"key":"2026081120143178000_RSOS252306C9","doi-asserted-by":"crossref","DOI":"10.4324\/9781315798721","volume-title":"Mechanisms of language acquisition: the 20th annual Carnegie Mellon symposium on cognition","author":"MacWhinney","year":"2014"},{"key":"2026081120143178000_RSOS252306C10","doi-asserted-by":"crossref","first-page":"323","DOI":"10.2307\/1585834","article-title":"Meaningful differences in the everyday experience of young American children","volume":"22","author":"Hart","year":"1997","journal-title":"Can. J. Educ."},{"key":"2026081120143178000_RSOS252306C11","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/89.985544","article-title":"Creating conversational interfaces for children","volume":"10","author":"Narayanan","year":"2002","journal-title":"IEEE Trans. Speech Audio Proc."},{"key":"2026081120143178000_RSOS252306C12","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2026081120143178000_RSOS252306C13","article-title":"KoNLPy: Korean natural language processing in Python","volume-title":"Proc. 26th Annu. Conf. Human & Cognitive Language Technology","author":"Park","year":"2014"},{"key":"2026081120143178000_RSOS252306C14","doi-asserted-by":"crossref","DOI":"10.1002\/9781444301007.ch22","article-title":"Acoustic analysis of speech","volume-title":"The handbook of clinical linguistics","author":"Kent","year":"2008"},{"key":"2026081120143178000_RSOS252306C15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.wocn.2018.07.001","article-title":"Introducing Parselmouth: a python interface to Praat","volume":"71","author":"Jadoul","year":"2018","journal-title":"J. Phonetics"},{"key":"2026081120143178000_RSOS252306C16","doi-asserted-by":"crossref","first-page":"385","DOI":"10.3758\/BRM.41.2.385","article-title":"Praat script to detect syllable nuclei and measure speech rate automatically","volume":"41","author":"De Jong","year":"2009","journal-title":"Behav. Res. Methods."},{"key":"2026081120143178000_RSOS252306C17","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"librosa: audio and music signal analysis in python","volume-title":"Proc. 14th Python in Science Conf. (SciPy 2015)","author":"McFee","year":"2015"},{"key":"2026081120143178000_RSOS252306C18","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Machine Learning","author":"Radford","year":"2023"},{"key":"2026081120143178000_RSOS252306C19","first-page":"12449","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Proc. Syst."},{"key":"2026081120143178000_RSOS252306C20","doi-asserted-by":"crossref","DOI":"10.1109\/SLT54892.2023.10023141","article-title":"Fleurs: few-shot learning evaluation of universal representations of speech","volume-title":"2022 IEEE Spoken Language Technology Workshop (SLT)","author":"Conneau","year":"2023"},{"key":"2026081120143178000_RSOS252306C21","first-page":"e00415","article-title":"Computational modelling of an optical character recognition system for Yor\u00f9b\u00e1 printed text images","volume":"9","author":"Oni","year":"2020","journal-title":"Sci. Afr."},{"key":"2026081120143178000_RSOS252306C22","volume-title":"Fuzzy string matching in Python","author":"Cohen","year":"2020"},{"key":"2026081120143178000_RSOS252306C23","doi-asserted-by":"crossref","DOI":"10.1109\/IAEAC.2017.8054419","article-title":"Research on string similarity algorithm based on Levenshtein Distance","volume-title":"2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conf. (IAEAC)","author":"Zhang","year":"2017"},{"key":"2026081120143178000_RSOS252306C24","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.patcog.2017.06.031","article-title":"Effective training of convolutional neural networks for face-based gender and age prediction","volume":"72","author":"Antipov","year":"2017","journal-title":"Pattern Recognit."},{"key":"2026081120143178000_RSOS252306C25","doi-asserted-by":"crossref","first-page":"241687","DOI":"10.1098\/rsos.241687","article-title":"Refining the prediction of user satisfaction on chat-based AI applications with unsupervised filtering of rating text inconsistencies","volume":"12","author":"Jung","year":"2025","journal-title":"R. Soc. Open Sci."},{"key":"2026081120143178000_RSOS252306C26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/JOEUC.300766","article-title":"Predicting user satisfaction of mobile healthcare services using machine learning: confronting the COVID-19 pandemic","volume":"34","author":"Lee","year":"2022","journal-title":"J. Org. End User Comput."},{"key":"2026081120143178000_RSOS252306C27","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1080\/02568549109594817","article-title":"The theoretical basis for relationships between language and literacy in development","volume":"6","author":"Snow","year":"1991","journal-title":"J. Res. Childhood Educ."},{"key":"2026081120143178000_RSOS252306C28","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511609664.008","article-title":"The challenge of academic language","volume-title":"The Cambridge handbook of literacy","author":"Snow","year":"2009"},{"key":"2026081120143178000_RSOS252306C29","article-title":"Supplementary material from: Analysing Korean children's speech data for early childhood educational services: age-specific insights from text and audio analysis","author":"Lee","year":"2026","journal-title":"Figshare"}],"container-title":["Royal Society Open Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/royalsocietypublishing.org\/rsos\/article-pdf\/doi\/10.1098\/rsos.252306\/6156053\/rsos.252306.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/royalsocietypublishing.org\/rsos\/article-pdf\/doi\/10.1098\/rsos.252306\/6156053\/rsos.252306.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:15:08Z","timestamp":1786493708000},"score":1,"resource":{"primary":{"URL":"https:\/\/royalsocietypublishing.org\/rsos\/article\/13\/8\/rsos252306\/482738\/Analysing-Korean-children-s-speech-data-for-early"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":29,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,12]]}},"URL":"https:\/\/doi.org\/10.1098\/rsos.252306","relation":{},"ISSN":["2054-5703"],"issn-type":[{"value":"2054-5703","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]},"article-number":"rsos252306"}}