arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11172cs.CLcs.SDeess.AS
收藏

使用zero-shot多语言机器翻译技术解决语音翻译中的数据不足

Tackling data scarcity in speech translation using zero-shot multilingual machine translation techniques

Mediaan

Tu Anh Dinh, Danni Liu, Jan Niehues

摘要:

最近,端到端语音翻译(ST)由于避免了错误传播而受到了极大的关注。然而,这一方法受到数据稀缺的影响。它严重依赖于直接ST数据,并且在利用语音转录和文本翻译数据方面效率较低,这些数据通常更容易获得。在多语言文本翻译的相关领域中,已经提出了用于zero-shot翻译的若干技术。其主要思想是增加不同语言中语义相似的句子的相似性。我们研究这些想法是否可以应用到语音翻译,通过建立ST模型训练语音转录和文本翻译数据。我们研究了数据增强和辅助损失函数的效果。这些技术成功应用于使用有限ST数据的Few-Shot ST,与直接端到端ST相比,BLEU点提高了+12.9,与从ASR模型微调的ST模型相比,BLEU点提高了+3.1。

英文摘要:

Recently, end-to-end speech translation (ST) has gained significant attention as it avoids error propagation. However, the approach suffers from data scarcity. It heavily depends on direct ST data and is less efficient in making use of speech transcription and text translation data, which is often more easily available. In the related field of multilingual text translation, several techniques have been proposed for zero-shot translation. A main idea is to increase the similarity of semantically similar sentences in different languages. We investigate whether these ideas can be applied to speech translation, by building ST models trained on speech transcription and text translation data. We investigate the effects of data augmentation and auxiliary loss function. The techniques were successfully applied to few-shot ST using limited ST data, with improvements of up to +12.9 BLEU points compared to direct end-to-end ST and +3.1 BLEU points compared to ST models fine-tuned from ASR model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑