On Knowledge Distillation for Direct Speech Translation

Understand

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.