Meta CEO Mark Zuckerberg gave a glimpse of the ongoing projects at Meta and how the Metaverse will look like in the coming future during the live streaming of “Inside the Lab: Building for the Metaverse with AI” event.
Zuckerberg revealed that Meta is working on building an AI-powered “universal speech translator” for the Metaverse that will work for everyone in the digital world. This project aims at streamlining users’ interactions who speak different languages in the digital universe with the help of AI.
“The goal here is instantaneous speech-to-speech translation across all languages, even those that are mostly spoken; the ability to communicate with anyone in any language,” Zuckerberg said during his presentation. “That’s a superpower that people dreamed of forever and AI is going to deliver that within our lifetimes,” he added, as reported by engadget.com.
Read More : Nokia PureBook Pro laptop with 12th-Gen Intel processor launched: Features, specs
According to the blog post by Meta, 20 percent of the world’s population does not speak languages covered by current translation tools. The other under-represented languages are difficult for AI tools to learn as they do not have enough written scripts for the machine learning (ML) algorithms.
For languages like English, Mandarin, or Spanish, apps and web tools already provide high-quality translation technology, but for other languages, it is not the case, the blog post said.
Meta’s universal language translator plan will be executed in two parts. In the first part, Meta is developing a “No Language Left Behind” program, a translation system capable of learning every spoken language even if there isn’t much text available to learn from.
“We are creating a single model that can translate hundreds of languages with state-of-the-art results and most of the language pairs, everything from Austrian to Uganda to Urdu,” Zuckerberg said during the live stream.
In the second, Meta aims to create an AI Babelfish, a universal speech translator that aims to build systems that directly translate speech in real-time from one language to another without the need for an intermediary written component.
However, data scarcity is the greatest obstacle for Meta when it comes to translation tools. The current systems for text translations rely on learning from millions of sentences of annotated data. Therefore, only a handful of languages that dominate the web are available for translation. Expanding to other languages creates a need to find ways to acquire and use training examples from languages with a sparse web presence, Meta wrote in its blog.
With these projects, Meta aims to improve translations so that people who speak different or even lesser-known languages can socialize in Metaverse.
