Papers › On Knowledge Distillation for Direct Speech Translation

On Knowledge Distillation for Direct Speech Translation

9 Dec 2020arXiv:2012.04964archive 2025-07-28

Marco Gaido, Mattia A. Di Gangi, Matteo Negri, Marco Turchi

Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT). For MT, one of the most promising techniques to transfer knowledge is knowledge distillation. In this paper, we compare the different solutions to distill knowledge in a sequence-to-sequence task like ST. Moreover, we analyze eventual drawbacks of this approach and how to alleviate them maintaining the benefits in terms of translation quality.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mgaido91/FBK-fairseq-ST officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Knowledge DistillationMachine TranslationSpeech RecognitionTransfer LearningTranslationspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections