European Stars and Stripes (Newspaper) - June 23, 1990, Darmstadt, Hesse                                How a speech recognition computer works when a person Speaks into the microphone the sound is first converted into electrical signals. Digital signal processing circuits then Sample the sound every 10 milliseconds. Statistical formulas Are used to generate three slightly different samples from a single Sample and comparisons of these Are then related to a Library of known digitized sounds. Once a sound has been reduced to several possible words it is compared to a Library of grammatical rules to increase the accuracy of the identification process. Voice recognition would make it possible for a computer to be directed by voice commands. By technology of the future talking to machines by Leslie Cauley Baltimore Sun speech recognition scientists Haven to produced anything to rival Hal the computerized leading Man in the movie classic 2001 a space Odyssey but they have devised some innovative uses for this new age technology that blurs the lines Between Man and machine. Defined As a computers ability to understand human conversation speech recognition is one of Many computerized tools available to businesses today for boosting efficiency and enhancing Bottom line results. According to experts the technology is ideally suited for the business Community because of its increasing ability to recognize and automatically Correct human errors a often without the assist of a person a that can exact heavy tolls from businesses in the form of lost Revenue and diminished customer Confidence. Speech recognition systems can also be used to facilitate communication with the Public a valuable tool for any business whose Revenue Stream hinges on customer relations Industry experts say. While the 10-year-old technology is still in its infancy by scientific standards the technology has its Early supporters in the business Community. Shearson Lehman Hutton american express Amtrak and Holiday inn Are among the businesses either experimenting with the technology or already using it. Dozens of hospitals throughout the United states also use speech recognition systems to track patients treatment. At one Massachusetts Hospital the speech system has been so effective in following up on patients admitted for emergency treatment that one insurance company reduced malpractice premiums for doctors by 20 percent through use of the system. As these systems become More sophisticated and More applications Are developed speech recognition will become a valuable resource for businesses of All types As Well As society at Large Many experts believe. A speech is Many a natural Means of communication Quot said David Pallette director of speech research at the National Institute of standards and technology. Quot its absurd to think that Man s Only communications with machines Are by manual Means by putting our fingers on silly keyboards. Speech recognition is the ultimate dream of communicating with  in 1990, the Industry Ideal embodied by Hal a a system with an unlimited vocabulary that recognizes continuous speech including Slang humor and double ent Endres a is still a Long Way from reality. While the problem of vocabulary size has almost been solved a a system produced by dragon systems inc. In Newton mass., offers a 30,000-Woru vocabulary which is More than most people need a other obstacles have proved More difficult to overcome. The most prickly of those is getting a computer to understand continuous human speech which tends to be inconsistent even with a single speaker and fraught with verbal hurdles that trip up even the most sophisticated of computers said Larry Rabiner director of speech research at Bell laboratories the research Arm of american Telephone amp Telegraph co. A in Star wars a remember the robot r2d2? a people talked to a machine just like they would a human Quot Rabiner said. Quot we re just not there yet and the technology a not going to be Here in anyone a lifetime who a alive  while other experts Are More optimistic about when that technology will be developed most agree that continuous speech is by far the most perplexing problem facing speech recognition researchers today. The reason even with a single speaker sounds Are variable. A person who says the word Quot the Quot several times within the same sentence for example wont say it exactly the same twice. That can throw off the computer which essentially builds its vocabulary by Quot listening Quot to a speaker recording the sound and then filing it away for future reference. Another problem is background noise experts note. Unless a speaker is in a soundproof room the computer has to figure out if the sound of a slamming door is a word or just extraneous noise. Another complicating Factor is the tendency of humans to run their words together speech researchers say. Thus a simple question like Quot what do you mean Quot May come out As Quot what Day mean Quot making it extremely difficult for a computer to interpret. Throw in regional accents Slang and a few double ent Endres and a computer can All but Short circuit trying to figure out what a speaker is saying said Robert Lucky executive director of research at Bell labs. Quot kids learn it on their own in the school Yard but we can to explain it Well enough for a computer to understand Quot Lucky said. Quot its a flawed technology Quot Rabiner agreed. Quot the Best you re going to do is get it right 99 percent of the  most speech recognition systems today require speakers to talk slowly with Short pauses Between words in a controlled environment that is relatively free of extraneous noise. Most systems Are also a speaker dependent Quot meaning that they must be trained to recognize the voice of a speaker. Training can be tedious taking several hours of repeating the same word until the computer can recognize it. The process must be repeated for each speaker who wants to use the system. Even with those limitations speech recognition scientists have produced some Bona fide Success stories. By most accounts the list is growing. At mercy Hospital in Springfield mass., for example emergency physicians started using a speech recognition system last year to prepare reports on patients admitted to the emergency room. Using four workstations and software supplied by Kurzweil applied intelligence of Waltham mass., emergency room doctors dictate patient information including symptoms to the computer. Based on that data the computer automatically asks questions and makes a Chart from the doctors responses. The doctor is notified by the computer of any diagnostic shortfalls. Likewise doctors Are notified when they Are treating a High risk patient with whom they should be especially careful. According to John Holbrook director of emergency room services at mercy the system has reduced the chances for errors amid the chaos of mercy a emergency room where one patient walks in about every eight minutes. Up to 80 percent of All hand written medical reports contain errors compared to less than 5 percent for computerized reports he said. The result malpractice premiums for doctors using the system have been reduced by 20 percent and documentation for the defense of medical malpractice suits has improved dramatically. Quot its a Miracle of technology because it really does work a Holbrook said. Page 16 a a a the stars and stripes saturday june 23,1990