SOTAVerified

ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition

2021-07-14Code Available0· sign in to hype

Afra Alishahia, Grzegorz Chrupała, Alejandrina Cristia, Emmanuel Dupoux, Bertrand Higy, Marvin Lavechin, Okko Räsänen, Chen Yu

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Tasks

Reproductions