Speech Recognition Technology free essay sample

An application of speech recognition technology in the healthcare industry is another section that this paper explores briefly. Please note that speech recognition technology in general recognizes speech and speaker, but this paper is concerned with speech recognition rather than speaker recognition. Keywords: SR, ASR, STT, Introduction In computer science, speech recognition (SR) is the translation of spoken words to text. It is also known as automated speech recognition (ASR), computer speech recognition, speech to text or just (STT) (Kirriemuir, 2003, Para. ). Some SR systems use training where an individual speaker reads section of text into the SR system. These SR systems are analyze the person’s specific voice and use it to fine tune the recognition of that person’s speech, resulting in more accurate transcription. Systems that do not use training are called â€Å"Speaker Independent† systems. Systems that use training are called â€Å"Speaker Dependentâ⠂¬  systems (Kirriemuir, 2003, Para. 4). A speech recognition system consists of the following: a microphone for the person to speak into, speech recognition software, a computer to take and interpret the speech, and a good quality soundcard for input and /or output. We will write a custom essay sample on Speech Recognition Technology or any similar topic specifically for you Do Not WasteYour Time HIRE WRITER Only 13.90 / page How does it work? Speech recognition is an alternative to traditional methods of interacting with a computer, such as textual input through a keyboard. In this system, an individual speaks into the microphone and the verbal message converted to text. The converted text can be stored, sent via email or printed out in hardcopy formats. SR has been given special attention in the healthcare industries for various reasons. In the healthcare industry, complete documentation and preservation of patient medical reports are vital and a benchmark that every healthcare facility has to meet. In order to meet this benchmark, providers need ample time to complete documentation on their patients. However, healthcare facilities are challenged with allocating enough time for providers to complete their charting. For this reason, healthcare facilities have been seeking a system that would facilitate this problem and improve charting efficiency. Currently, SR software that has two functions is considered to be a preferred system for the healthcare field. In the healthcare field there are two types of SR systems that are used frequently. These are front-end and back-end or deferred SR systems (Edinburgh, n. d. ). Front-end speech recognition is where the provider dictates into a speech-recognition engine; the recognized words are displayed as they are spoken; and the dictator is responsible for editing and signing off on the document. Back-end or deferred speech recognition is where the provider dictates into a digital dictation system. The voice is routed through a speech recognition machine and the recognized draft document is routed along with the original voice file to the editor, where the draft is edited and report finalized. Advantages SR system is also recognized for its remarkable benefits. Entering data to the computer requires some type of input, whether it is text or voice. Speech is preferred as an input because it does not require training and it is much faster than any other input. It is also a very natural way to interact and it does not necessitate acquiring additional skills, like typing. The SR system can replace or reduce the reliability on standard keyboard and mouse input. Furthermore, this system can be exceptionally useful for people with some difficulties such as: people with little keyboard skills or experience; people with dyslexia, or others who have problems with character or word use and manipulation in a textual form; and people with physical disabilities that affect either their data entry or ability to read what they have entered. The main benefit advertised by voice recognition software producers s increased word processing speed. According to the Writer’s Store website, the average person types about 40 words per minute but can dictate 120 words per minute (Edinburgh, n. d. ). For those who have challenges with typing or a physical disability, being able to speak commands to a computer or send an email without having to press a key can make a computer vastly more enjoyable to use (Kirriemuir, 2003, Para. 2). Disadvantages SR system is an innova tive technology; however, it is not without potential problems or disadvantages. Initially, the software has to be trained to recognize the user’s voice. It is accomplished by reading the passage into the computer for accurate voice recognition. However, if a person training the software struggles with words and makes frequent reading mistakes, the software will make mistakes when dictating. If the user has non-standard speech, tends to run words together or mumbles, then the training process may take longer. The software spells every word it recognizes correctly; however, 5 – 20% words are recognized as incorrect (Kirriemuir, 2003, P. 4). For example, it cannot recognize homonyms- words such as two, to, too. As the result some words and punctuations must be edited. Voice recognition uses a lot of memory and needs specific hardware installment. Also people with thick accents may not be able to achieve accurate word recognition. In a loud environment, voice recognition software may fail to recognize the user’s voice, and it may even try to generate text from voice heard in the background. These problems make the SR less desirable to implement in many corporate industries including the healthcare field. Costs Purchasing speech recognition software is not beyond the reach of one’s budget. The cost of the SR system varies from the types of software intended to use. Generally, the cost ranges from free to couple thousands of dollars; this makes it cheaper than buying a keyboard and a mouse. As the result many companies are willing to try the system. Current users Although many companies are still testing this product, there are institutions that are using it extensively. These include the U. S military, FAA, the healthcare industries, Banks, and other retail corporations. Current Vendors There are several vendors that are manufacturing the system, mainly in the United States and the UK. The top leader SR vendors are Microsoft Corporation (Cicrosft Voice Command), Digital Syphon (Sonic Extractor), LumenVox, Nuance Communication (Nuance Voce Control), Speech Technology Center, Vito Technology (VITO Voice2Go), Speereo Software (Speereo Voice Translator), Verbyx Vrx and SVOX. Conclusion Speech recognition technology is the translation of spoken words to text. It is an alternative to traditional methods of interacting with computer, such as textual input through a keyboard. This system has received special attention in the healthcare industry, mainly for its capability to input text into the computer much faster than traditional typing method. Although the system has a lot of problems, organizations like the U. S. military still utilize it due to its low cost. This system has made dictation much easier for various individual and is a hope for more effective documentation. References University of Edinburgh. (n. d. ). Mobiusing advanced technologies for care at home. Retrieved on November 30, 2012, from http://www. cs. stir. ac. uk CNN (2000, May 12). Technology is voice recognition dangerous for your health. Retrieved on November 13, 2012, from http://http://articles. cnn. com/2000-05-23/tech/voice. saving. tips. idg_1_speach-recognition-dragon-systmes Kirriemuir, John. (2003, March 30). Speech Recognition Technologies. Retrieved on November 30, 2012, from www. Jisc. ac. uk