We present the visually-grounded language modelling track that was introduced in the Zero-Resource Speech challenge, 2021 edition, 2nd round. We motivate the new track and discuss participation rules in detail. We also present the two baseline systems that were developed for this track.
Cite
@article{arxiv.2107.06546,
title = {ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition},
author = {Afra Alishahi and Grzegorz Chrupała and Alejandrina Cristia and Emmanuel Dupoux and Bertrand Higy and Marvin Lavechin and Okko Räsänen and Chen Yu},
journal= {arXiv preprint arXiv:2107.06546},
year = {2021}
}