Embedded Files
We aim to assess how experiences affect children’s language development,
developing open-source machine-learning tools
applied to 10,000+ hours of child-centered recordings.
Who are we?
The ExELang project is led by Alex Cristia, Research Director at CNRS, and head of the Language Acquisition Across Cultures team (Laboratoire de Sciences Cognitives et de Psycholinguistique, Département d’études cognitives, ENS, EHESS, CNRS, PSL University). Thanks to an ERC Consolidator grant, over the next 5 years, we'll be hiring two engineers, two PhD students, one post-doctoral fellow, and a part-time project manager. We will also be setting up an ethics review board soon, that periodically checks that the project is complying with the highest ethical standards. (See also this page.)
Interested in joining us? More information here or by emailing alecristia@gmail.com .
What do we do?
In this project, we'll re-use data that has been gathered, or that is being gathered, to understand how experiences infants and young children have affects their language development. We are particularly interested in long-form audio-recordings, collected with a wearable device over many hours. These recordings give a child-centered view of the speech the child hears and says, and they do not require any effort from the child or the family. We'll start with 10 corpora, represented in the table on the right.
Interested in contributing data? See our call for data for more information.
Page updated
Google Sites
Report abuse