Google claims that once you snap the photo of an object, the AI translation app Woolaroo will utilize machine learning to translate it into one of 10 endangered languages supported on the app.
Queensland-based Yugambeh Museum has worked with Google Arts and Culture to build an open-source, artificial intelligence-based digital language tool called Woolaroo that is designed to preserve endangered languages.
AI translation app Woolaroo is built using Google Translate and Cloud Vision. This tool utilizes image processing and machine learning to translate photos of objects into natural languages in real-time. If several objects are identified in a photo, users can scroll through the objects and choose the translation depending upon each object.
Yugambeh Museum CEO Rory O’Connor wrote a blog post,
“Given the importance of Aboriginal language to Australian culture, we have the incentive to record the known but in particular new words our community members are using as the world evolves bringing us new technology we didn’t have before.”
Besides being able to translate, Woolaroo has additionally been built to encourage individuals and communities to offer new words and audio recordings to help with pronunciation.
Additionally, O’Connor said, the Woolaroo app offers Indigenous communities the power to add, edit, and delete entries entirely in their hands. This way people can react promptly to newly memorized words and phrases and add them straight into the dictionary.
The language supported on Woolaroo APP incorporates Yugambeh, an Aboriginal language spoken in Queensland and New South Wales, Louisiana Creole, Calabrian Greek, Māori, Nawat, Tamazight, Sicilian, Yang Zhuang, Rapa Nui, and Yiddish. The AI translation app can translate these languages into English, French, or Spanish.