Language Preservation 2.0: Crowdsourcing Oral Language Documentation using Mobile Devices
Thousands of languages are falling out of use. Every time this happens we lose a unique perspective on the world. A unique story about how people have lived in a particular place, passed down by word of mouth over the generations.
Language Preservation 2.0 is about applying new research in social media to the grand challenge of recording, transcribing, and translating the world’s languages. New recording technology running on mobile devices helps remnant communities to make sure their language can be heard, understood, and learnt by future generations. It is the least expensive and most scalable method for archiving hundreds of hours of spoken language.
The project’s first app, Aikuma, supports voice-activated recording and translation. The resulting database may one day serve as an audio “Rosetta Stone”, making it possible to decipher newly discovered recordings from long-forgotten languages. The data we collect will be housed in the Language Commons a multimedia collection that is part of the Internet Archive.
This project is sponsored by the US National Science Foundation, the Swiss National Science Foundation, and the Australian Research Council.