Loïc Barrault

TL;DR: A conditional compute model based on Sparsely Gated Mixture of Experts that is trained on data obtained with novel and effective data mining techniques tailored for low-resource languages is developed, laying important groundwork towards realizing a universal translation system.

TL;DR: For each shared task of the 19th International Conference on Spoken Language Translation, the purpose of the task, the data that were released, the evaluation metrics that were applied, the submissions that were received and the results that were achieved are detailed.

TL;DR: This paper shares a massive amount of unlabeled audio data (671 hours) in five languages: French from Niger, Fulfulde, Hausa, Tamasheq and Zarma, and a smaller 17 hours parallel corpus of audio recordings in TamAsheq, with utterance-level translations in the French language.

TL;DR: The authors proposed to use a method that evaluates the percentage of the source contribution to a generated translation to identify translations that are disconnected from the source, hence they can be identified by low source contribution.

TL;DR: This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and dialect speech translation and highlights that self-supervised models trained on smaller sets of target data are more effective to low- resource end-to-end ST fine-tuning, compared to large off-the-shelf models.