Loading ...
Sorry, an error occurred while loading the content.

[TECHNOLOGY] International Verbal Translator Device of 125 Languages

Expand Messages
  • madchinaman
    INTEGRATED WAVE TECHNOLOGIES, INC. http://www.i-w-t.com/ - A soldier speaks into the headset, English is translated into one of 125 languages and then
    Message 1 of 1 , Dec 23, 2006


      A soldier speaks into the headset, English is translated into one of
      125 languages and then broadcast from a small speaker engineered for
      high noise environment. VRT tucks into an M4 single ammo pouch.

      MilTrans VRT / 202.549.3096 / 202.441.0791 / info@...
      Integrated Wave Technologies / 4042 Clipper Ct / Fremont, CA /
      Timothy McCune / President, Chief Technologist
      timothy@... / 202 549 3096
      Laura Madonna / Marketing, Sales, Training
      laura@... / 202 441 0791
      Cindy Cook-Johnson / Business Manager
      cjohnson@... / 510-353-0260


      Special Report
      IWT President Tim McCune announced that the Voice Response
      Translator, with megaphone attachment, was tested by the Navy in
      Norfolk for force protection applications. The initial Weapons
      Officer Reported "The device works great, this is a very nice and
      unexpected addition to [the ship,s] force protection capability."

      This system has since put to sea on several Navy vessels. More
      extensive testing is continuing.

      Voice Response Translator Deployed by USCG in Gulf Action
      "It has proved to be the best interpreting tool that we have used to
      date. Others have been purchased for us, but yours is used all of the
      time. It is simple to program, easy to use and the voice that
      results from the unit is clear and understandable to the end user -
      the Arabic vessels that we encounter each day"

      22nd MEU Testing Results
      "The Marines who employed the VRT give it credit for being a very
      rugged unit that can stand the rigors of being a permanent part of
      battle gear, getting bumped and dropped, and still function properly."

      "It was exposed to extreme heat in excess of 95 degrees with greater
      than 80 percent humidity. It weathered rain and thunderstorms for up
      to one hour in the open. It shows no signs of problem."

      Metro Nashville Police Department
      "The IWT device responds well in high background noise where other
      speech recognition systems would not work at all."
      Kenneth Pence, Captain



      Voice ResponseTranslator is the only combat proven, eyes-free, hands-
      free voice recognition system allowing a user to maintain situational
      awareness and weapons readiness.

      Imagine you're a soldier in Baghdad, don't speak Arabic and you must
      shout a command to a pack of angry-looking insurgents: "Drop your
      weapons!" You could fire warning shots, or take out a handheld
      computer and use a stylus to scroll through a list of preprogrammed
      phrases on a touchscreen and then flip the device around to show
      enemy combatants the command in Arabic. Not what you want to do in a
      hostile situation or combat zone.

      MilTrans VRT tactical eyes-free, hand-free one and a half way voice
      translator is the solution. The device is stand alone; MICH/ACH
      Integrated; or Integrated into Headset with Phased Array System and

      Applications include providing instructions during force protection,
      house/vehicle searches, combat patrol, civil aid missions, entry
      control duty, basic medical triage, ship boarding and prison control.

      Integrated Wave Technologies, (IWT)
      MilTrans VRT is produced by IWT, a Fremont, CA-based company, that
      specializes in the development and production of miniaturized speech
      recognition devices that work in high noise environments.

      IWT was founded in 1992 by Silicon Valley pioneer John H. Hall, who
      developed the first successful electronic watch, the first
      computerized heart pacemaker, the first radiation-hardened computer
      and other civilian and defense electronics systems.

      The 11-ounce VRT was developed over the past 12 years with National
      Institute of Justice and Defense Department funding and has been
      field tested, receiving strong positive feedback from Police, Green
      Berets, SEALs, Rangers, Marines, USCG personnel and others in combat
      deployment and law enforcement tactical missions.

      IWT continues to develop speech recognition technology in the
      advancement of miniaturized tools for military, medical, and law
      enforcement personnel facing language barriers today. Read more…


      About Us


      MilTrans VRT is the next generation of voice recognition technology
      from Integrated Wave Technologies (IWT),a high technology company
      focusing exclusively on sound analysis-related R&D, marketing and
      production. MilTrans high-power processors provide precision eyes-
      free, hands-free capability, along with flexible foreign language
      recognition and continued low power consumption.

      Integrated Wave Technologies (IWT) develops all software and hardware
      internally and concurrently for MilTrans VRTs. Software and hardware
      complement each other and create synergies with respect to accuracy,
      noise immunity, size and power consumption. Each generation VRT
      builds on successful design work of previous generations while
      advancing the state of the art.

      IWT Founder's Background

      John Hall has nearly 40 years of semiconductor design work and over
      60 fundamental patents, including pioneering work in low-power CMOS
      integrated circuit technology.

      He co-founded Intersil with Fairchild Eight member Dr. Jean Hoerni
      and led all technical development there.

      He has developed advanced electronics for medical, military,
      telecommunications and other industries. His decisive technological
      advantages to cutting-edge devices include:

      CMOS technology and electronic watch application (Seiko);
      First computerized heart pacemaker (Medtronic)
      First electronic camera shutter (Canon)
      First printing calculator (Seiko)
      First pocket pager types (Harris, Kokusai)
      Cellular phone technology (Nokia)
      First Radiation-Hardened Computer
      First Dielectric Isolation IC
      Developed Low Cost Chip Assembly for B-1b Bomber Phased Array Radar
      Control Module
      Assembly for Westinghouse Defense Systems
      Infrared Focal Plane Sensor Array for Aerojet General


      Investment Growth Opportunities

      Integrated Wave Technologies, Inc. (IWT), is a high technology
      company that focuses exclusively on sound analysis-related R&D,
      marketing and production. The company is based in Fremont,
      California, and it has additional research facilities in St.
      Petersburg, Russia. It has acquired highly advanced sound analysis
      technology from sources in the former Soviet Union and has adapted
      and advanced this technology in its own research facilities. These
      facilities are capable of software development, prototype
      development, and custom-designed chip fabrication.

      The company's Chairman and Chief Executive Officer is John H. Hall.
      Hall has over 30 years of advanced electronics research experience
      and has made significant contributions to advancements in the state-
      of-the-art both in basic semiconductor technology and in chip-based
      applications of this technology. Among his innovations are the first
      low-voltage CMOS chip, a design that Seiko purchased and mass
      produced beginning in 1970. Hall has continued to make advancements
      in CMOS and other electronics technology in both commercial and
      classified defense programs.

      Hall has significant experience in managing start-up high-technology
      companies. He was co-founder of Intersil with Fairchild Eight member
      Jean Hoerni in 1968, heading its research and development, with work
      that included a breakthrough in coating silicon oxide gates with
      phosphorous glass and creating the first practical metal oxide
      semiconductor (MOS) processes. Intersil also developed the first N
      Channel memory chip, which was later adopted as an industry standard.

      Hall founded Micro Power Systems in 1971 with work that included low-
      power CMOS integrated circuit designs that he used in the first
      computerized programmable heart pacemaker and the first electronic
      camera shutter, the first low-cost ICs highly resistant to nuclear
      radiation, stationary phased array radar systems, frequency
      synthesizers, handheld digital voltmeters, portable LCD calculators,
      molybdenum gate MOS process used for cellular phone construction, and
      the first one-chip analog-to-digital converters. While he was
      president of MPS from 1971 to 1986, the company grew at an average
      rate of 25 percent a year with no external debt or equity funding.
      From 1986 to the present, Hall has been Chairman and Chief Executive
      Officer of Linear Integrated Systems, Inc., specializing in bipolar
      linear and high-speed CMOS digital circuits.

      IWT has developed several new voice-related technologies that are
      uniquely effective for certain highly demanding applications. The
      first technology is a voice recognition algorithm and related
      implementation technology. The second is a biometric technology that
      allows for the precise identification of individuals. The third
      technology is a speech compression technology that allows for voice
      recordings to be contained in vastly smaller digital files.

      These technologies are not merely superior to those of other
      companies. They cross performance thresholds that will allow them to
      be the basis of new products and new markets. In addition to
      securing ownership of the algorithms, IWT has pursued an aggressive
      strategy of developing essential implementation technologies. The
      Company is in the process of completing patent application
      documentation for these technologies and believes that the resulting
      patents will prevent competitors from developing similarly capable

      These technologies also can be combined with existing innovations
      such as the Universal Serial Bus standard and emerging ones such as
      the Bluetooth radio frequency interface standard to become important
      integrated parts of the next generation of computing systems.

      Several new market opportunities are based upon IWT's ability to
      build very compact, low-cost devices that recognize all languages,
      dialects and impairments in speech in environments with loud and
      unpredictable background noise. The core technology was developed in
      the former Soviet Union in a atmosphere where expensive and
      complicated resources were limited. Russian scientists were forced
      to use inferior (by Western standards) computing machinery. To get
      results, they had to rely on elegant, yet parsimonious, algorithms to
      achieve comparable results being accomplished in the West with more
      powerful computers. IWT acquired the applicable rights to this
      technology in 1994 and continues to fund related research.

      There are two characteristics that differentiate this voice
      recognition technology from those available in the United States.
      First, the Soviet technology uses sound analysis to recognize
      commands. Western systems use phonemes -- parcels of speech -- to
      recognize words through approximate comparisons and probability
      analysis. Each vowel or consonant or blend sound heard by the
      computer is matched to a template of phonemes. These phonemes are
      assembled and matched to possible words. But the phoneme-based
      systems have a high error-substitution rate and are highly
      susceptible to interference from background noise.

      IWT's system analyzes the frequency and energy characteristics of the
      sounds rather than the phonemes. This allows IWT to match sounds
      directly and precisely to templates of voice commands and also to
      distinguish the voice command sounds from all types of background
      noise, even other human speech.

      The second characteristic is the highly efficient architecture of the
      Soviet algorithm. Software based on this algorithm can run on
      relatively modest hardware -- a 286 processor compared with Pentiums
      require for Western voice recognition systems -- which means that IWT
      has been able to create systems that are vastly smaller, more power
      efficient and cheaper than systems relying on Western systems. The
      algorithm can be embedded in a single chip, which can then be
      integrated directly into devices where voice command is desired.
      Western systems were forces to rely on large, costly laptop Pentium
      computers that use a significant amount of power to integrate voice
      command into other systems.

      Based upon these two characteristics, IWT has been able to create new
      market opportunities by meeting the stringent requirements of
      carefully selected applications. Currently available voice
      recognition systems are unable to meet the demands of these
      applications, and IWT's technical success can create a monopoly in
      these specific areas. IWT has worked closely with federal government
      technology managers, federal laboratory engineers, university
      technology application specialists, industry experts and non-profit
      organization experts to ensure ability of its voice recognition to
      meet the requirements of these market opportunities.

      IWT adopted this strategy of pursuing high-end, demanding
      requirements unmet by current voice recognition systems after
      determining that the poor performance of devices put on the market by
      other companies had created a negative image of all voice recognition
      systems in the minds of many computer users. These projects both
      create important products and benchmark this technology as being
      clearly superior to all other voice recognition. IWT believes that
      after it demonstrates its capabilities through demanding, high-
      profile applications, it will be able to sell applications for
      general use, either through computer manufacturers or as discrete
      items through software and hardware retailers.

      IWT has developed prototypes for five such initial applications,
      including two selected over all other voice recognition systems for
      use in federal law enforcement technology programs by high-level
      review panels. Though some of these applications are for small niche
      markets, they were chosen because the technology is transferable
      easily to mass-market products such as personal digital
      assistants/palm computers.

      The first application is plug-in speech recognition for personal
      digital assistants such as the Handspring Visor. IWT can provide
      near-perfect speech recognition for command/control and data entry
      for these devices in a compact package interfacing easily with the
      handheld computer.

      The second application is a "caddy" to allow portable cellular phones
      to be used with voice commands in vehicles. IWT's prototype is the
      first device to be miniaturized to fit within the existing form
      factor for non-voice command caddies already in use and the first to
      work in the high noise environment that characterizes most vehicles.
      The target market is the general population, with sales conducted
      through phone service providers, phone manufacturers and automobile
      electronic aftermarket retail outlets. IWT believes that the
      substantial expected market penetration could be boosted by pending
      state and federal safety legislation. This legislation would make it
      illegal to use cellular phones while driving a vehicle and likely
      would be passed with an exception for voice-command units. Fully
      developed prototypes have been built and production would begin six
      months to one year after receiving funding.

      This application was selected by a National Institute of Justice peer
      review panel for funding with respect to providing voice-command
      cellular phones patrol officers in cars, on motorcycles and on
      bicycles. This testing effort, which for the first time provides
      voice command telecommunications for these high-noise environments,
      is ongoing.

      The IWT recognition technology has an additional characteristic
      important for this application and others. Section 255 of the
      Telecommunications Act of 1996 has laid out soon-to-be-enforced
      requirements for telecommunications equipment to be accessible to and
      usable by people with disabilities, if it readily achievable for a
      manufacturer to make it so. IWT's algorithm is uniquely capable of
      recognizing impaired speech. The United Cerebral Palsy Association
      has endorsed IWT's speech recognition for this application, as have
      Senate Small Business Committee Chair Bond and Senate Aging
      Committee. IWT is also working with the President's Committee on
      Employment of Persons with Disabilities with respect to applications
      of this technology. IWT believes that these already enacted laws
      will provide it with a significant competitive advantage.

      IWT's unique cellular voice command capability would have
      significance in the event that concerns over electromagnetic
      radiation bioeffects prove to have merit. Studies have indicated
      correlation between the 0.5 to 2 watt electromagnetic transmissions
      from hand-held cellular phones and brain cancer, though these studies
      are disputed by the cellular phone industry and others. At a
      distance of one meter or more from the transmission antenna, however,
      the signals fall to a level that all parties agree is safe. Use of
      voice command would allow for cellphone use that would allay concerns
      over electromagnetic safety.

      The third application is a belt-mounted, voice command language
      translation device, the first such technology ever produced. The
      translator plays pre-recorded translations of selected foreign
      language phrases when commanded by a police officer's voice. This
      translator is being tested by the Oakland Police Department in a
      program funded by the Justice Department's National Institute of
      Justice Science and Technology Office. The test device has over 500
      phrases, each in three foreign languages. This device's target
      market is the 600,000 sworn law enforcement officers in the U.S.
      Other markets to be targeted initially include emergency medical
      technicians, U.S. military personnel and foreign police and armed
      forces. The translator is ready for mass production.

      It is important to note that the Justice Department listed voice
      command translation as one of the top priorities for law enforcement
      technology development after years of extensive surveys of local
      police departments. The Department awarded IWT grants totally
      approximately $950,000 to develop this application based on its
      conclusion that the IWT system would provide a unique, effective
      solution to a critical law enforcement problem.

      The fourth application involves plug-in voice-command interfaces for
      desktop/laptop/palm computers. These devices would provide highly
      capable voice command-and-control capability that interfaces with
      computers through their Universal Serial Bus (USB) ports in the case
      of desktops and laptops, and through the serial interface of palm

      This approach has several significant advantages over running the
      voice recognition on these computers. First, by creating plug-in
      stand-alone hardware/software packages, users don't need to load the
      software onto their computer. Second, this approach allows IWT to
      bypass the computer's sound card and control aspects of sound
      process. Most sound cards are unsuited for the delicate task of
      speech recognition, and this approach allows for unprecedented
      accuracy. Third, this approach allows users to use their voice
      control device on various computers at work and home. While this is
      important for all persons, it is especially so for disabled persons
      and will allow for this application to be promoted by the Section 508
      provisions. Fourth, this allows IWT to prevent unauthorized use,
      piracy, of its software.

      This application involves assistive technology for disabled persons
      with impaired speech. Two years of demonstrations and tests with a
      physical therapy center for such persons has shown that IWT's voice
      recognition technology has a unique capability to recognize impaired
      speech accurately. Devices developed to the prototype stage are
      units to convert impaired speech voice commands into recognizable
      English and command-and-control units for use with televisions,
      telephones and computers. This would allow speech-impaired disabled
      persons to lead more productive work lives and more independent home
      lives. The target market is the approximately 10 million persons who
      suffer varying degrees of disabilities and speech impairs as the
      result of conditions such as cerebral palsy, multiple sclerosis,
      Parkinson's Disease, Acquired Brain Injury, strokes, epilepsy and

      IWT is testing new prototypes with the Cerebral Palsy Association of
      Greater St. Louis. The national United Cerebral Palsy Association
      has evaluated this technology also and has promised to market devices
      produced through the 160 member associations and also through its
      Internet catalog of assistive devices. IWT is confident that once
      produced, this technology will become a standard for "reasonable
      accommodation" under the Americans with Disabilities Act and the
      Individuals with Disabilities Education Act and will be required for
      use in workplaces and schools for disabled persons with and without
      impaired speech.

      IWT anticipates the market for services and high-technology hardware
      for disabled persons to be a significant business area. Some 52
      million non-institutionalized Americans experience some form of
      disability that impairs their performance of daily activities. While
      many of these disabilities are relatively minor, approximately 26
      million Americans are "severely" disabled.

      According to marketing date taken from recent studies by FIND/SVP, a
      25-year-old worldwide research and consulting firm, this market is
      now estimated to be $796 billion and will top $1 trillion in the next
      five years. Functional limitations affect 36 million persons, and
      work disabilities affect 17 million.

      The adoption of IWT's voice command capability as a reasonable
      workplace accommodation under the Americans with Disabilities Act
      will add to this market size. The majority of people with
      disabilities are of working age, but only one-third of disabled
      persons are employed and most of these are in blue-collar
      occupations. Employed people with disabilities earn less than their
      peers. Voice command will open new areas of employment in high-tech,
      computer-based jobs. This will offer new opportunities for many
      large groups. For example, visual impairments affect more than 10
      million, and more than two million have impaired speech.

      The fifth application is for portable and desk-mounted voice command
      assistance for computer programming and application modification.
      IWT's near-100% accuracy rate allows it to be used to insert pre-
      packaged parcels of computer code during programming. This allows
      programmers to increase their productivity significantly and to an
      extent far greater than if "hot keys" are used for code parcel
      insertion (12 hot keys versus an unlimited number of voice commands
      that would probably be set at 1,000). An ongoing demonstration
      project being conducted by IWT in conjunction with a computer network
      maintenance company has shown that the time needed for a typical
      network software upgrade was reduced from six hours to one-and-a-half
      hours. The target market would be companies that perform computer
      programming and application modification. This capability would have
      to be sold on a case-by-case basis for many users, and IWT is seeking
      to form a partnership with a larger company that focuses on providing
      computer service.

      IWT's selection of highly credible partners and/or advisors in each
      of the application areas means that its ability to serve these
      markets has been validated by credible experts. This will assist any
      potential investor greatly with respect to due diligence evaluations
      and in the eventual marketing and sales of these products.


      Xeni Tech
      By Xeni Jardin
      Tech Solutions to Iraqi-U.S. Language Barrier

      Day to Day, November 13, 2006 · Part of the daily struggle for
      soldiers and Marines in Iraq is communicating with civilians and
      suspected insurgents. Few military personnel have enough fluency with
      Iraqi Arabic to be easily understood, and field translators are in
      short supply.

      But technology may help close that communications gap. A hand-held
      voice translator device developed by Integrated Wave Technologies,
      already in use in other parts of the world, converts simple English
      commands into Iraqi Arabic or 15 other languages.

      When the soldier says a simple phrase -- for example, "keep kids
      back" -- the Voice Response Translator (VRT) matches that command to
      a more complex phrase in Arabic. In this case: "Keep your children
      back from us or we will take action against you."

      Integrated Wave Technologies President Tim McCune says simple
      communications like these can save lives, both among Iraqi civilians
      and military personnel. "This removes pulling the trigger as the
      first option in dealing with foreign nationals," he says.

      Dr. Mari Maeda, a researcher at the Defense Advanced Research
      Projects Agency (DARPA) says the government has spent $15 to $20
      million a year over the past five years developing the mobile
      translator technology, because there aren't enough human translators
      to go around. Critics say the Defense Department should instead spend
      its dollars training troops how to speak Arabic or other languages.

      One advantage of these portable translation devices is that they can
      be programmed by a local interpreter to fit different missions. John
      Hall, president of Annapolis-based Voxtech International, makes a
      similar device called the Phraselator.

      Hall believes technology can help a military unit make better use of
      one human interpreter. "You don't have to keep [the translator] there
      in potential harm's way all the time," he says.

      What soldiers say they really could use are small, hands-free devices
      that translate speech in both directions, as people talk to them.
      DARPA has some early prototypes of such a device, but they are at
      least a decade away from being combat-ready.


      First Ears, Then Hearts and Minds
      Facing Shortage of Arabic Interpreters, Pentagon Seeks a
      Technological Solution

      By Renae Merle
      Washington Post Staff Writer

      For science-fiction buffs, it's probably a common-sense solution. Two
      months after arriving in Iraq, a second lieutenant with the 16th
      Military Police Brigade was handed the Phraselator, a hand-held
      device that promised to digest his English phrases and produce a
      prerecorded Arabic translation with an Iraqi accent.

      But after a brief test last year, the soldier gave up the gadget,
      deciding that, while helpful in some instances, it wasn't useful to
      his unit, which conducted raids and provided convoy security. He had
      even tried to teach himself Arabic using the device but decided that
      it was no match for the complex language. Even such simple phrases
      as "What is your name?" are spoken differently in Fallujah than in
      Baghdad, he found. "This may have been the reason why many of the
      Iraqis . . . did not appear to understand the Arabic phrases & words"
      stored in the device, according to a report prepared for the Army.

      An Annapolis firm, VoxTec International Inc., developed the device
      and said it has steadily made improvements. But the goal of having a
      machine replace a human interpreter remains elusive, and the military
      is mounting a multimillion-dollar campaign to find a more capable
      successor, one that can translate both sides of a conversation, from
      English to Arabic and vice versa.

      "What people would really like is that 'Star Trek' universal
      communicator, but it doesn't exist yet," said Lynne McCann, former
      chief of the Army Foreign Language Proponency Office. "That would
      solve everything."

      The stakes are high for the military, which suffers from such a
      shortage of interpreters that it has had to rely increasingly on
      contractors -- 6,500 in Iraq and 1,500 in Afghanistan. It can be a
      dangerous job. Of the 648 contractors killed in Iraq since the war
      began in March 2003, 153 worked for the division of L-3
      Communications Corp. that currently holds the linguist contract,
      according to Labor Department figures.

      Battlefields often turn into impromptu laboratories for new
      technologies -- with mixed results. During the Persian Gulf War in
      1991, the Patriot anti-missile system was rushed into combat to
      intercept Iraqi scuds, but afterward, investigators questioned its
      effectiveness. The Predator, an unmanned drone, dropped Hellfire
      missiles after the Sept. 11, 2001, terrorist attacks, after a quick
      development process.

      In the same way, VoxTec, which was a unit within Marine Acoustics
      Inc., was asked to rush production of its Phraselator, then a single
      prototype, shortly after the attacks on New York's World Trade Center
      and the Pentagon, said Ace Sarich, the company's vice president of
      development. The device is about the size of a large personal digital
      assistant and is programmed with about 700 Arabic phrases that can be
      recalled after it "hears" the equivalent English phrase or a soldier
      chooses a sentence from a text list on the device.

      The company shipped 20 to Afghanistan within a few months, but the
      prototypes had bugs, including buttons that were hard to push and
      faulty batteries. "It was supposed to be a weatherproof design, and
      it leaked like a sieve," Sarich said. Those issues have all been
      addressed, he added.

      While VoxTec continued to improve the device, the military began
      testing a device made by a California company, Integrated Wave
      Technologies Inc. It had developed a similar hands-free version of a
      translation machine that fit into an ammunition pouch, allowing
      soldiers to say key phrases that are then turned into full Arabic

      "You say 'house search' and then it will say in Arabic: 'We're here
      to search your house. Please stay in this room. Do you have any
      weapons?'" said Tim McCune, the company's president.

      Over the past few years, Integrated Wave Technologies has produced
      1,300 of its machines and VoxTec has made 5,000 devices. They cost
      about $2,500 to $3,000 apiece, a mini-boom for two companies that
      have fewer than 20 employees each.

      Neither product, however, proved robust enough to replace human
      interpreters. What soldiers really needed, the military decided, was
      to have a conversation with the people they encounter, not just give

      "In years past, there wasn't a great need for the individual soldier
      to speak a foreign language to do his mission," said Wayne Richards,
      branch chief for technology implementation at U.S. Joint Forces
      Command. But in Iraq and Afghanistan, soldiers are increasingly
      interacting with Iraqi civilians, giving advice at checkpoints or
      guidance during home searches, he said.

      "During those door-to-door searches, the soldiers need to be able to
      calm them down and reassure them," Richards said. "We're fighting for
      hearts and minds. But if I can't tell her, 'Ma'am, please calm
      down,' . . . that wouldn't be assuring."

      So the Pentagon turned to the Defense Advanced Research Projects
      Agency (DARPA), which helped develop the Internet, to enlist some
      technology powerhouses, setting aside $20.8 million this year for
      translation technologies. Military officials said they do not expect
      the automated devices to completely replace human interpreters but to
      augment them. DARPA was a natural fit to lead the project because it
      has spent the past two years creating a database of thousands of
      hours of Iraqi conversations to study the voices, speech patterns and
      commonly used phrases to help with speech-recognition software.

      The agency selected SRI International, a nonprofit research group,
      International Business Machines Corp., and Carnegie Mellon University
      in Pittsburgh to help put that database to work.

      Each of the three has developed systems that use mathematical
      algorithms to interpret speech, even if it is slurred, accented or
      muffled, into Arabic and the Arabic response into English. After a
      second or two, a synthesized male voice produces a response. The
      systems usually require speakers to limit their conversations to one
      sentence at a time to avoid confusion.

      IBM announced this month that 35 units of its system had been shipped
      to Iraq, saying it would "facilitate quick" communication. The
      military is not quite as optimistic.

      The systems are being tested only in offices or benign situations
      with limited background noise, military officials said.

      The technology is "just not ready for wide deployment," said Mari
      Maeda, program manager in DARPA's Information Processing Technology
      Office. "The translation system is not good enough; the recognition
      software is not strong enough."

      The systems are also not accurate enough, she said. IBM estimates
      that its system has an accuracy rate of 85 to 90 percent, and that
      out of 30 phrases, a person may need to repeat four or five. SRI and
      Carnegie Mellon officials said they couldn't provide comparable
      figures. But "soldiers are looking for things that work 95 percent of
      the time," Maeda said.

      In the meantime, companies are also experimenting with lower-tech
      solutions. VoxTec, for instance, is testing a call-a-translator
      system in Baghdad that allows soldiers to call in from the field so
      they can put an Iraqi on the phone with one of two Arabic translators
      on duty who can act as an intermediary.

      Integrated Wave Technologies says it may have another interim
      solution. It is developing a system, which DARPA says it may send to
      Iraq next year, that will enable limited two-way conversations
      by "listening" for key words, said McCunne, the company's president.
      But even that, he acknowledges, has problems.

      "If you ask, 'What color was the car?' it will be looking for
      something like blue or red," he said. But if the person responds by
      asking which car or says he didn't see a car, the system will not be
      able to translate, McCunne said. "It's a fairly limited type of
      communication," he added.
    Your message has been successfully submitted and would be delivered to recipients shortly.