Program Objective:

The goal of the Babylon program is to develop rapid, two-way, natural language speech translation interfaces and platforms for the warfighter for use in field environments for force protection, refugee processing, and medical triage. Babylon will focus on overcoming the many technical and engineering challenges limiting current multilingual translation technology to enable future full-domain, unconstrained dialog translation in multiple environments.

Program Strategy:

The Babylon seedling project, “RMS,” or Rapid Multilingual Support, was deployed to Afghanistan in the spring of 2002. The Babylon program will focus on low-population, high-terrorist-risk languages that will not be supported by any commercial enterprise. Mandarin and Arabic were selected based on immediate and intermediate needs.

Planned Accomplishments:

• FY 02: In direct support of field operations, Babylon will build and rapidly deploy one-way speech translation systems for four target languages: Pashto, Dari, Arabic, and Mandarin. Systems will be delivered in the form of militarized palm-sized PDA devices (12 hour battery endurance) that conform to the military uniform ensemble.
• FY 02: Each of four Babylon two-way translation teams will develop ten domain (task)-constrained, natural language translation prototypes hosted on multiple platforms. Each system will undergo an evaluation process and the successful teams will advance and continue to refine their system through technology patches and insertions.
• Follow-on years will expand the domains, or tasks, supported by the Babylon prototypes, and improve their robustness and responsiveness to field requirements.

Related Links:

• DARPA Babylon Site
• Charles Wayne, "Human Language Technology TIDES, EARS, Babylon" at DARPATech 2002
  • slides (PDF 1.6mb)
  • script (PDF 76kb)
• EFF Mirror: Charles Wayne, "Human Language Technology TIDES, EARS, Babylon" at DARPATech 2002
  • slides (PDF 1.6mb)
  • script (PDF 76kb)