The richness of little voices: using artificial intelligence to understand early language development
The authors have withdrawn this manuscript because it was realized that the central classification result that we claimed was attributable to a phenomenon of shortcut learning in which the recording conditions for the audios used could have been the main source of information for the classifier, rather than the actual content of the child vocalizations, which was our target. Therefore, the authors do not wish this work to be cited as reference for the project. If you have any questions, please contact the corresponding author.
neuroscience↗