This is a excerpt from some research I did on growing technologies in the classroom. Part 1 follows, I will post the other parts in the days to come, the sources will be included with the last part.
The world has changed dramatically in the last fifty years, from the typewriter to the keyboard, to cell phones, and now to the introduction of voice recognition and speech recognition. The way that people do business is constantly changing and a challenge for business teachers is to stay on top of emerging technologies to ensure that students are equipped with relevant skills when they enter the workforce. New methods for inputting data are going to be a major change in the business world. How are teachers going to be able to teach their students these new technologies? They will need to understand the technologies and how they relate to the business world, as well they will need to adapt to the way they have to teach students the new methods.
What is Voice Recognition?
“Speech recognition is an alternative to traditional input methods that outperforms all previous options” (Effective Methods of Teaching Business Education in the 21st Century 125). That is to say that speech recognition is a new technology that is more efficient than older and current input methods such as keying. The average person currently keys at a speed of 30 to 45 WPM, which is the speed most used as a requirement for jobs requiring keying. Meanwhile most human beings speak at a speed of 200 WPM in normal conversation (Words per minute). That is four to six times faster than the average person can key. Although it is true that humans can speak at a rate of 200 WPM most voice recognition software has people averaging speeds of 110 to 170 WPM (Effective Methods of Teaching Business Education in the 21st Century 125).
Such great speeds can make the business world a much more efficient place. Currently at speeds of 45 WPM it would take 10 minutes to key a 450 word document, while it would take a meager 3 or 4 minutes to speak that same document, that saves over half the amount of time it takes to key a document. Five minutes might not seem like much, but when you take someone like a secretary who keys quite a bit it can save lots of time. As an example if a secretary keys 450,000 words a year, that would take 10,000 minutes to key whereas if the secretary used speech recognition software it would take approximately 2650 minutes. That is an astounding 123 hours less time over the year.
The value of speech recognition is enormous, if a business could save 123 man hours every year to be used somewhere else they would be ecstatic. It would be economical for businesses and everyone in general to use speech recognition as the definition of economics is “economics is the study of the use of scarce resources which have alternative uses” (Sowell 1). Well the secretary in this example is the scarce resource and the secretary could have alternative resources.
How does Voice Recognition work?
Voice or Speech recognition is “the process by which a computer identifies spoken words” (Cook "Introduction"). This is to say that it basically works by having a user speak into the computer and then have the computer interpret what it receives from the user. The user will use a microphone to input the speech into the computer through the sound card. It is recommended that the user uses a quality microphone, such as a headset microphone, to reduce ambient noises that could change the way the computer software interprets the sounds it receives from the user (Cook “Hardware”).
Once the sound has reached the software what does it do with it? Voice recognition software is broken up into two different types: Pattern Recognition, which compares patterns to patterns that have been previously trained into the software, and Acoustic Phonetic, which uses programmed knowledge of the human mechanics of speech and then compares that with human speech features (Cook “Inside Speech Recognition”).
No comments:
Post a Comment