Many speech translation systems rely on transcriptions.

许多语音翻译系统依赖于转录。

In general, AI-powered translation systems have improved greatly in recent years.

总体而言，人工智能翻译系统近年来有了很大的改进。

Generally, developers of translation systems train AI models on very large amounts of written text in the target languages.

通常，翻译系统的开发人员会根据目标语言的大量书面文本来训练人工智能模型。

These tools will enable other researchers to create their own speech-to-speech translation systems and build on our work.

这些工具将使其他研究人员能够创建自己的语音到语音翻译系统，并在我们的工作基础上再接再厉。

Zuckerberg said in a video that effort is designed to create translation systems to cover " hundreds" of world languages.

扎克伯格在一段视频中表示，这个项目旨在创建涵盖“数百种”世界语言的翻译系统。

Meta said it aims to use the same methods used for Hokkien to create speech-to-speech translation systems for many more languages in the future.

Meta表示，它的目标是在未来使用与闽南语翻译系统相同的方法为更多语言创建语音转语音翻译系统。

Applying computers to language studies has resulted in machine translation systems and machines that recognize and produce speech and text.

将计算机应用于语言研究产生了机器翻译系统和机器，这些机器能够识别和产生语音和文本。

Some problems remain. In the real world, people talk over one another, use slang or chat on noisy streets, all of which can foil even the best translation system.

问题仍然存在。在现实生活中，人与人之间的交谈相互重叠，夹杂着俚语或是在吵闹的大街上说话，这些都能让最先进的翻译器无能为力。

The translation system is part of our Universal Speech Translator project, which is developing new AI methods that we hope will eventually allow real-time speech-to-speech translation across many languages.

该翻译系统是我们 “通用语音翻译系统”（ Universal Speech Translator） 项目的一部分，该项目正在开发新的人工智能方法，我们希望这些方法最终能够实现跨多种语言的实时语音到语音翻译。

To address this challenge, we've built the first AI-powered speech-to-speech translation system for Hokkien, a primarily oral language that's widely spoken within the Chinese diaspora but lacks a standard written form.

为了应对这一挑战，我们为闽南语构建了第一个人工智能语音到语音翻译系统，闽南语是一种主要的口头语言，在海外华人中广泛使用，但缺乏标准的书面形式。