论文标题
端到端语音翻译的课程预培训
Curriculum Pre-training for End-to-End Speech Translation
论文作者
论文摘要
端到端的语音翻译对编码器造成了沉重的负担，因为它必须同时转录，理解和学习跨语性语义。为了获得功能强大的编码器，传统方法将其预先培训在ASR数据上以捕获语音特征。但是，我们认为，仅通过简单的语音识别进行预训练编码器还不够，因此应考虑高级语言知识。受此启发的启发，我们提出了一种课程预培训方法，其中包括用于转录学习的基本课程以及两个高级课程，以理解两种语言的话语和映射单词。这些课程的困难正在逐渐增加。实验表明，我们的课程预培训方法可对En-DE和En-FR语音翻译基准进行显着改善。
End-to-end speech translation poses a heavy burden on the encoder, because it has to transcribe, understand, and learn cross-lingual semantics simultaneously. To obtain a powerful encoder, traditional methods pre-train it on ASR data to capture speech features. However, we argue that pre-training the encoder only through simple speech recognition is not enough and high-level linguistic knowledge should be considered. Inspired by this, we propose a curriculum pre-training method that includes an elementary course for transcription learning and two advanced courses for understanding the utterance and mapping words in two languages. The difficulty of these courses is gradually increasing. Experiments show that our curriculum pre-training method leads to significant improvements on En-De and En-Fr speech translation benchmarks.
