We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography. We study the replacement of orthographic transcriptions by images and/or translated text in a well-resourced language to help unsupervised discovery from raw speech.
@article{arxiv.1802.05092,
title = {Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop},
author = {Odette Scharenborg and Laurent Besacier and Alan Black and Mark Hasegawa-Johnson and Florian Metze and Graham Neubig and Sebastian Stueker and Pierre Godard and Markus Mueller and Lucas Ondel and Shruti Palaskar and Philip Arthur and Francesco Ciannella and Mingxing Du and Elin Larsen and Danny Merkx and Rachid Riad and Liming Wang and Emmanuel Dupoux},
journal= {arXiv preprint arXiv:1802.05092},
year = {2018}
}