Advertisement
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.”
G/O Media may get a commission
Advertisement
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.