论文标题
关于直接语音翻译的知识蒸馏
On Knowledge Distillation for Direct Speech Translation
论文作者
论文摘要
直接语音翻译（ST）已证明是一项复杂的任务，需要从其子任务中转移知识转移：自动语音识别（ASR）和机器翻译（MT）。对于MT而言，转移知识的最有希望的技术之一是知识蒸馏。在本文中，我们将不同的解决方案比较了在序列任务（如ST）中提取知识的不同解决方案。此外，我们分析了这种方法的最终缺点，以及如何减轻他们在翻译质量方面保持好处。
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.
