image of this article category

Meta develops new Speech-to-Speech Real-Time Audio Translation Process

24.10.2022 09:51 AM
Latest
Meta develops new Speech-to-Speech Real-Time Audio Translation Process
dooklik website logo
share
share this article on facebook
share this article on twitter
share this article on whatsapp
share this article on facebook messenger
Meta develops new Speech-to-Speech Real-Time Audio Translation Process

Meta, announced that it has developed a non-standard Taiwanese language translation system, in a first step within the social network's giant project to develop an automatic voice translation tool that works in real time and in all languages.

"This technology allows Taiwanese-speaking people to exchange conversations with English-speaking people," the giant American group said in a statement.

The informatics program is still not completed, and at this stage it allows translating one sentence at a time, but this is "a first step towards a future in which simultaneous translation of languages will be possible," according to the company.

Taiwan is spoken by more than 30 million people in Taiwan and other Asian regions, according to the National Institute of Oriental Languages and Civilizations in Paris.

Meta explained that this language does not adopt a standardized writing system, similar to "more than 40% of the nearly seven thousand living languages" in the world.

Current AI technologies for machine translation need to analyze large amounts of written text to work well.

Meta's statement pointed out that its researchers specializing in artificial intelligence "faced many obstacles, from collecting data to developing a graphic model to evaluating" the results.

The researchers used Mandarin as an intermediate language to conduct correspondence and ensure that their system translates oral speech directly, without going through writing.

The American group intends to use its own Taiwanese translation system as part of its "Global Translator" project, and will put its information codes at the disposal of other researchers in artificial intelligence.

Meta pointed out in a statement that her Universal Speech Translator project, known as "UST", aims to "contribute to bringing down barriers and bringing people together wherever they are."

Related Articles
doolik website logo
Meta has disabled a feature in its AI image generation tool just days after announcing it, following widespread backlash from users and major creative organizations.

doolik website logo
Before becoming an official product, Meta is reportedly testing a new prototype of AI-powered smart glasses, internally called "Super Sensing." The glasses are designed to continuously monitor what users see and hear, offering powerful memory and search capabilities—but also raising significant privacy concerns.
doolik website logo
The future of wearable technology has arrived and it's more stylish than ever. Meta has unveiled the Meta Glasses Starfire, the first and only AI-powered smart glasses featuring Meta AI voiced by Kylie Jenner. Designed to seamlessly blend fashion with cutting-edge technology, Starfire redefines what smart eyewear can be.
Live Video Streaming
Live video streaming lets you engage with your audience in real time with a video feed. Broadcast your daily show to your audience with no limits, no buffering and high quality videos. Reach all devices anytime anywhere with different video qualities that suits any device and any connection.
$1,120/YE*
The website uses cookies to improve your experience. We’ll assume you’re ok with this, but you can opt-out if you wish.
ACCEPT