BBN gets $17M to finish DARPA’s GALE project to boost fast foreign language translation
Raytheon’s BBN Technologies this week got a $17 million contract to finish a five-year project that will result in a software system that can transcribe, translate and distill large volumes of speech and text in multiple languages – all with more than 90% accuracy.
BBN has been developing the Defense Advanced Research Projects Agency (DARPA) Global Autonomous Language Exploitation (GALE) program which will ultimately offer a system that can translate foreign language material (television shows and newspapers) in near real-time, highlight salient information, and store the results in a searchable database. In the end GALE should help US analysts recognize critical information in foreign languages quickly so they could act on it in a timely fashion. BBN has gotten about $50 million from DARPA to develop GALE.
According to DARPA, GALE technology will make it possible for English speakers to do much of what foreign language operators and analysts do now: convert large quantities of “undecipherable” foreign language data into timely, actionable intelligence in English (for operational planning, crisis response, and force protection). This will provide commanders and other decision makers with vital information that was previously unavailable.
Raytheon BBN said under this latest contract award, it will continue to improve translation of speech and text from Arabic and Chinese news sources.
“DARPA’s GALE program is already responsible for many great advances in machine translation, and BBN has deployed systems for monitoring live broadcasts in foreign languages in more than two dozen locations. This new funding will allow us to achieve an even higher level of machine translation accuracy,” said Tad Elmer, president, Raytheon BBN Technologies in a statement.
The GALE system is only one of a number of DARPA language translation systems under development.
DARPA in Feb., said it was looking to build technology that can accurately – 99% of the time — listen to speech patterns, detect key words, identify the language and speaker in highly degraded, weak or noisy communication channels. The system, called Robust Automatic Transcription of Speech (RATS) will be composed of a variety of software development and speech processing algorithms that specialize in Arabic, Farsi, Pashto, Dari and Urdu, DARPA said.
Existing transcription and translation and speech signal processing technologies are insufficient for working with noisy or degraded speech signals, DARPA stated. Currently, there is no technology that effectively addresses this kind of noisy and distorted speech signal, so operational units are forced to allocate significant human resources for this task. Operators are frequently working “in the dark,” searching blindly over thousands of possible channels at any given moment without prior knowledge of the quality, relevance or language contained in the signal, if there is any signal at all, DARPA stated.
The agency says the government has “a compelling need for reliable, relevant information to directly support intelligence gathering in the field, to inform military decision makers and respond to national security requirements.”
The ideas is that real-time language translation technology will help US forces better understand adversaries and overall social and political contexts of particular situations. This improved awareness will decrease costly mistakes due to misunderstandings, and of course let us in on nefarious activities.
Check out these other hot stories:
- Beyond the petaflop: DARPA wants quintillion-speed computers
- Can X Prize help deliver Gulf region from BP oil disaster?
- Four critical US cybersecurity projects that need constant pressure
- IBM research project looks to reshape mobile email
- Mars may have been 1/3 ocean
- US Coast Guard calls for tech help in BP oil disaster
- FTC bombs massive robocall operation
- BP oil spill disaster data available online from US Dept. of Energy
- NASA gets front row seat for fiery “man-made meteor” reentry
- Can your data center earn an EPA Energy Star?
- FAA adds brainpower to mix unmanned aircraft with commercial aviation
