DARPA taps BBN Technologies for language translation work

With the United States involved in military operations around the globe, quickly translating foreign language speech and texts into useful information for military officials is critical.

BBN Technologies of Cambridge, Mass., has won a $16.4 million contract from the Defense Advanced Research Projects Agency to develop a system that will solve the problem of transcribing speech and computer-encoded text directly into English text so that soldiers, commanders and other decision-makers will have quick access to such information.

The project is part of DARPA's Global Autonomous Language Exploitation initiative. The goal of the initiative is to develop and apply computer software technologies to absorb, analyze and interpret huge volumes of speech and text in multiple languages.

The new system will include automatic transcription of both speech and text communications and also will filter the resulting English text for needed data, the company said.

BBN will integrate the components into a single process instead of using the traditional linked approach of speech-to-text followed by machine translation and distillation. The goal of the system is to adapt to different languages, dialects, topics, speakers and semantic nuance.

Ethan Butterfield is a staff writer for Government Computer News' sister publication, Washington Technology.

inside gcn

  • power grid (elxeneize/Shutterstock.com)

    Electric grid protection through low-cost sensors, machine learning

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group