Meta is chugging along on their Universal Speech Translator, which hopes to train an artificial intelligence to translate hundreds of languages in real time. Today, the tech giant claims to have generated the first artificial intelligence to translate Hokkien, which is a language primarily spoken and not written.
Hokkien is a language that is spoken by approximately 49 million people in countries like China, Taiwan, Singapore, Malaysia, and the Phillippines. Typically, training an AI to understand human speech—and in Meta’s case, translation—researchers will feed the computer a large dataset of written transcripts. But Meta says that Hokkien is once of nearly 3,500 languages that are primarily spoken, meaning Hokkien does not have a large enough dataset to train the artificial intelligence since the language does not have a unified writing system.
We’re developing AI for real-time speech translation to break down language barriers in the physical world and in the metaverse.https://t.co/PC0BzLCHAr pic.twitter.com/wW8NlyndmM
— Meta Newsroom (@MetaNewsroom) October 19, 2022
As such, Meta focused on a speech-to-speech approach, as explained in the company’s press release. Without going into too much detail, Meta explained that the input speech was translated into a sequence of acoustic sounds, which was then used to create waveforms of the language. Those waveforms were then coupled with Mandarin, which Meta identifies as a “related language.”
Meta says that the Hokkien translator is still a work in progress as the artificial intelligence can only translate one sentence at a time, but is being released as open-source so other researchers can build upon its work. The company is also releasing SpeechMatrix which is a “large collection of speech-to-speech translations developed through our innovative natural language processing toolkit.”
Meta’s efforts at building tech to understand human language has a bit of a wonky past. The company released BlenderBot 3 earlier this year to show their attempt at creating an artificial intelligence chatbot. A previous investigation by Gizmodo found that the bot’s favorite movie was Mean Girls and that it really wanted you to know that racism is bad.
