speech recognition

921 Words2 Pages

Speech is the common basic way we communication with each other. The development of voice biometrics is one that emerged to allow a user to input their voice into a computer system. It is a growing technology which provides security in computers. A speech recognition system is designed to assist the user to complete what that person wants to say versus having a person transcribe it. The first step in voice recognition is for the user to be trained and produce an actual voice sample. Through this process sounds, words or phrases are converted in electrical signals and then they are turned into a coding process by the system. The goal of voice recognition is to understand the human spoken voice. Speech recognition has a long history that actually began in the toy industry. The first toy to respond to voice commands with voice recognition was named Radio Rex. It was created by the Elmwood Button Company in 1922. The first speech recognition systems could understand only digits because of the different types of human language. Bell Laboratories designed the "Audrey" system in 1952, which recognized digits spoken by a single voice. Years later, IBM Company introduced its "Shoebox" machine, in 1962. This system could understand 16 words spoken in English. Then in the 1970s, speech recognition expanded with Siri Speech recognition technology, from the U.S. Department of Defense. They also developed the “DARPA” Speech Understanding Research (SUR) program, from 1971 to 1976, which was one of the largest research programs in the history of speech recognition. In the 1980s, speech recognition took a new approach to understanding what people were saying. Speech recognition vocabulary increased from a few hundred words to several thousand w... ... middle of paper ... ...quire usage of different skills. They will become editors of the EHR reports and will remain responsible for the quality of information that was dictated into the system. They would use what is known as front-end speech recognition (FESR). The use of speech recognition technology has increased in the last decade in the field of medical transcription, but it will not replace the traditional medical transcription system because of the number of problems that occur while using the new technology. In conclusion, the main benefit of voice recognition is the extra added level of security that it provides its consumers. This technology is very secure but most of all software programs have its problems as it grows. In time I am sure it will become one of the most successful software applications in the large expanding field of electronic documentation and health records.

Open Document