arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1912.03393cs.CLcs.AIcs.LG
收藏

长文同声传译的重译策略

Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation

Google Research(谷歌研究院)

Naveen Arivazhagan, Colin Cherry, Te I, Wolfgang Macherey, Pallavi Baljekar, George Foster

摘要:

我们研究的问题,同时机器翻译的长形式的语音内容。我们的目标是一个连续的语音到文本的场景,生成翻译字幕的现场音频饲料,如讲座或播放的评论。由于这种情况允许对增量翻译进行修改,因此我们采用了重新翻译的方法来进行同声翻译,即随着源代码的增长,从头开始重复翻译。这种方法自然表现出非常低的延迟和高的最终质量,但代价是随着输出的不断改进而增加不稳定性。我们使用工业级语音识别和翻译工具的管道进行实验,并使用简单的推理算法来提高稳定性。我们使用TED演讲作为多语言测试数据的来源,开发我们的英语到德语口语翻译技术。我们的最低限度同步翻译方法使我们能够轻松地将最终评估扩展到另外六种目标语言,从而显著提高所有语言的增量稳定性。

英文摘要:

We investigate the problem of simultaneous machine translation of long-form speech content. We target a continuous speech-to-text scenario, generating translated captions for a live audio feed, such as a lecture or play-by-play commentary. As this scenario allows for revisions to our incremental translations, we adopt a re-translation approach to simultaneous translation, where the source is repeatedly translated from scratch as it grows. This approach naturally exhibits very low latency and high final quality, but at the cost of incremental instability as the output is continuously refined. We experiment with a pipeline of industry-grade speech recognition and translation tools, augmented with simple inference heuristics to improve stability. We use TED Talks as a source of multilingual test data, developing our techniques on English-to-German spoken language translation. Our minimalist approach to simultaneous translation allows us to easily scale our final evaluation to six more target languages, dramatically improving incremental stability for all of them.

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。

↑