Home Title Page Introduction Background Information Potential Benefits Potential Problems Conclusion Bibliography IT 103 Research Paper PDF Research Paper Blog Research Paper Wiki

Automatic Speech Recognition
Background Information
stack of books


As previously stated, automatic speech recognition was only launched decades ago, to be specific, in the 1950s. “Bell laboratories designed in 1952 the “Aubrey” system, which recognized digits spoken by a single voice” (Pinola, 2011). Notice that only a single voice could be used when first tested on the recognition software because the technology at that time was not advanced enough to understand more than one pitch or even different sexes. Numbers are also the most general form of communication when speaking verbally because they only represent quantities rather then expressions and feelings. Numbers can be communicated in many other forms even with quick universal hand signals of holding up your fingers. Not until 1962, did IBM create its “Shoebox machine, which could understand sixteen words spoken in English” (Pinola, 2011). Transitioning from numbers to words was a huge advancement because those sixteen words were the first step in the human language being basic commands, which in the field of an answering service is a huge help because it can decide whom the caller specifically needs to talk to and narrow down what they need help with. A major step was in 1976 when the “U.S. Department of Defense funded the DoD’s DARPA Speech Understanding Research (SUR) program…it was responsible for Carnegie Mellon’s “Harpy” speech understanding system. Harpy could understand 1011, words, approximately the vocabulary of an average of a three-year old” (Pinola, 2011). At this point in time, a development on interpretation different voices was made as well as understanding fully formed sentences. The Department of Defense funded this research and program in hopes for their benefit to use the software for themselves. Their funding was obviously beneficial and brought much progress to past research. Years went by and automatic speech recognition worked its way further and further into commercial applications such as dictionaries and the business world until today where its part of our everyday activities.


PREVIOUS PAGE
NEXT PAGE

Valid XHTML 1.0!