arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.06155cs.CLcs.SDeess.AS
收藏

IWSLT 2021 BUT语音翻译系统

The IWSLT 2021 BUT Speech Translation Systems

Brno University of Technology(布尔诺理工大学)

Hari Krishna Vydana, Martin Karafi'at, Luk'as Burget, "Honza" Cernock'y

摘要:

本文介绍了BUT为IWSLT 2021开发的英语到德语离线语音翻译(ST)系统。它们基于联合训练的自动语音识别-机器翻译模型。它们的性能在MustC-Common测试集上进行了评估。在这项工作中,我们从具有大量单独的ASR训练数据和MT训练数据以及少量的语音翻译训练数据的角度来研究它们的效率。大量的ASR和MT训练数据被用于预训练ASR和MT模型。语音翻译数据用于通过定义从语音到翻译的端到端可区分路径来联合优化ASR-MT模型。为此,我们使用ASR解码器的内部连续表示作为MT模块的输入。我们表明,语音翻译可以进一步提高训练ASR解码器联合MT模块使用大量的纯文本MT训练数据。我们还通过训练能够生成标点文本的ASR模块,而不是将标点任务留给MT模块来显示显着的改进。

英文摘要:

The paper describes BUT's English to German offline speech translation(ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on MustC-Common test set. In this work, we study their efficiency from the perspective of having a large amount of separate ASR training data and MT training data, and a smaller amount of speech-translation training data. Large amounts of ASR and MT training data are utilized for pre-training the ASR and MT models. Speech-translation data is used to jointly optimize ASR-MT models by defining an end-to-end differentiable path from speech to translations. For this purpose, we use the internal continuous representations from the ASR-decoder as the input to MT module. We show that speech translation can be further improved by training the ASR-decoder jointly with the MT-module using large amount of text-only MT training data. We also show significant improvements by training an ASR module capable of generating punctuated text, rather than leaving the punctuation task to the MT module.

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。

↑