Reverse engineering language acquisition with child-centered long-form recordings

Bibliographic Data

ID19040353
AuthorsMarvin Lavechin (0000-0002-6005-9368, Centre National de la Recherche Scientifique), Maureen de Seyssel (0000-0003-2345-5676, Centre National de la Recherche Scientifique), Lucas Gautheron (0000-0002-3776-3373, Centre National de la Recherche Scientifique), Emmanuel Dupoux (0000-0002-7814-2952, Centre National de la Recherche Scientifique), Alejandrina Cristia (0000-0003-2979-4556, Centre National de la Recherche Scientifique)
Year2021
Publication date2021-03-31
Open AccessNo
TypePREPRINT
PublisherCenter for Open Science (PUBLISHER)
DOI10.31234/osf.io/pt9xq
OpenAlexW4247178956
LanguageEN
Citations received5
References cited9

Language use in everyday life can be studied using lightweight, wearable recorders that collect long-form recordings - that is, audio (including speech) over whole days. The hardware and software underlying this technique is increasingly accessible and inexpensive, and these data are revolutionizing the language acquisition field. We first place this technique into the broader context of the current ways of studying both the input being received by children and children’s own language production, laying out the main advantages and drawbacks of long-form recordings. We then go on to argue that a unique advantage of long-form recordings is that they can fuel realistic models of early language acquisition that use speech to represent children's input and/or to establish production benchmarks. To enable the field to make the most of this unique empirical and conceptual contribution, we outline what this reverse engineering approach from long-form recordings entails, why it is useful, and how to evaluate success

Data acquisition · Human–computer interaction · Programming language · Wearable computer · Computer Science · Speech and Audio Processing · Speech and dialogue systems · Speech Recognition and Synthesis · Software

Tools

Open DOIOpen Access