Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts

Rebekka Hubert, Artem Sokolov, Stefan Riezler. Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts. In Elizabeth Salesky, Marcello Federico, Marine Carpuat, editors, Proceedings of the 20th International Conference on Spoken Language Translation, IWSLT@ACL 2023, Toronto, Canada (in-person and online), 13-14 July, 2023. pages 89-101, Association for Computational Linguistics, 2023. [doi]

Abstract

Abstract is missing.