Email	Print Reprint
	add to:
	Del.icio.us Digg Google Furl	Slashdot Y! MyWeb Blink

National Institute of Standards and Technology (NIST) researchers are evaluating prototype, real-time, two-way translation systems for the Defense Advance Research Projects Agency (DARPA).

The DARPA program, called "TRANSTAC" (Spoken Language Communication and Translation System for Tactical Use), is being developed to help the U.S. military overseas communicate with people who speak different languages. The initial target language is Iraqi Arabic. From July 16 to 20, NIST ran a series of laboratory and outdoor evaluation tests on prototype systems with English-speaking U.S. Marines and Iraqi Arabic speakers. In each of the exercises, NIST measured system capabilities in speech recognition, machine translation, noise robustness, user interface design, and efficient performance on limited hardware platforms. In operation, a Marine speaks an English utterance into a TRANSTAC system. The system recognizes his/her speech, translates the words into Iraqi Arabic, and speaks that utterance to an Arabic speaker. The Arabic speaker then speaks their response and the same process occurs again (except from Arabic to English).

"Effective two-way translation devices would represent a major advance," according to Craig Schlenoff, project leader of the NIST evaluation project. "Although American forces in Iraq currently have the use of phrase-based translators, the devices can only translate English into prerecorded Arabic phrases. They cannot translate Iraqi Arabic into English," he said.

During the NIST laboratory and field tests, the Marines and Iraqi Arabic speakers acted out 10 different scenarios -- ranging from traffic checkpoints to neighborhood surveys -- that required verbal communication. Individuals in the laboratory tests looked directly at each other during the question and answer sessions. Although their audible conversation was recorded on a laptop, neither party could see the screen. Iraqi Arabic speakers, who understood English, also wore earphones that blocked out the English language query and, instead, relayed only the system's Arabic interpretation of the question. Background sounds were tightly controlled, so that the systems could be evaluated in a predictable environment.

The outdoor evaluations included background noises -- such as other speakers, generators, opening garage doors, running vehicles, and radio broadcasts -- and simulated more realistic conditions. The military personnel also carried the translator devices in backpacks or in another hands-free manner, approximating future hardware developments that should provide American forces with small (even palm-sized) translators that would not require attention or interfere with their ability to stay alert.

These exercises follow an earlier assessment from an NIST independent evaluation team in January and February 2007. The early evaluation involved over 75 participants including 10 Marines, 10 Native Arabic speakers, and multiple members of five different evaluation teams (i.e., IBM, SRI, Sehda, BBN, and Carnegie Mellon University).

Once the technology is fully developed, DARPA hopes to be able to develop an automatic translator system in a new language within 90 days of receiving a request for that language.

RELATED ARTICLES IBM Releases Annual 'Next Five in Five' Quantum Computing Spins Closer Center for Music Technology Launched World's Fastest Bar Code Reader Developed Surveyor Intros Low-cost 3D Stereo Vision for Robotics and Web		TOP 5 ARTICLES No Top Articles.