Technology
Meta Launches Artificial Speech Translation to Aid Communication Among People Who Speak Different Lanuguages
Meta has announced the launch of its universal speech translator (UST), which aims to create AI systems that enable real-time speech-to-speech translation across all languages.
American multinational technology company Meta has announced the launch of its universal speech translator (UST), which aims to create AI systems that enable real-time speech-to-speech translation across all languages.
Following the launch of its first speech translator, Meta seeks to enable ease of communication among people who speak different languages, even those that are not commonly written.
Speaking on the launch of its first AI-Powered speech translator, the CEO of Meta Mark Zuckerberg said, “Meta AI built the first speech translator that works for languages that are primarily spoken rather than written. We’re open-sourcing this so people can use it for more languages.”
The company disclosed that the newly launched AI-powered speech translation system was for the unwritten Chinese language ‘Hookkien’, a language spoken in the southeastern part of China and Taiwan.
The system allows Hokkien speakers to hold conversations with English speakers, which is a significant step towards breaking down the global language barrier and bringing people together wherever they are located.
The company said in a blog post, “Until now, AI translation has focused on written languages. Yet, of the more than 7,000 living languages, more than 40 percent of languages are primarily oral and do not have a standard or widely known writing system.
“We plan to use our Hokkien translation system as part of a universal speech translator and will open source our model, code, and training data for the AI community to enable other researchers to build on this work.”
Meta further disclosed that this model is still a work in progress as it is a positive step towards the future where simultaneous translation between languages is possible.
The company disclosed that it is releasing the speech matrix, a large corpus of speech-to-speech translations mined with Meta’s innovative data mining technique called Laser, which will enable researchers to create their speech-to-speech translation.
As the world rapidly advance digitally, Artificial speech translation has become a rapidly emerging technology with top technology companies such as Microsoft and Alphabet rolling out speech-to-speech AI translation model.