Article 9; Is voice becoming the new text (again)?

Today’s blog is a review of an article written by John D. Sutter of CNN. The article is titled: “Is voice becoming the new text (again)?” In the article, the author delves into the subject of voice recognition in mobile phones and other devices. Discussion as to how advanced the technology has become is looked at first. David Nahamoo, IBM's chief technology officer for voice research, had something to say about it. He said that current technology works by “listening to a voice, translating it into digital data and then anticipating what sorts of sounds or words will come next”. The major difference between this style of voice decoding and the original technology delivered years ago is that the early versions “tried to understand every sound and used huge amounts of computing power as a result”. Obviously, due to the sheer magnitude of the required data storage and handling in those days, the technology did not take the world by storm.
The new technology uses a totally new approach to lessen the amount of data needed to be analyzed and dealt with. “It’s more of a guessing game. Each voice-recognition program has a number of equations that analyze speech and use statistics to decide what noises match up to what letters”. The question that still remains however is “Are we at a point in the advancement of this technology that voice could actually replace or be an alternative to texting?”
The author leaves it to you to be the judge of that, but does inform the reader of a recent study done to determine the accuracy of the technology. “Meisel found that technologies that translate voice into text are roughly 80 to 90 percent accurate. That's good enough for many common functions, like transcribing voice mail, he said.”
One of the main concerns for supporters of the technology is the required processing power. Even with the major strides to reduce the burden, it would still take “a better, higher-end phone to do it.” The other problem is that different people “speak with accents or colloquialisms or different languages or stuff like that, which provides some challenges as well”. In spite of the hurdles, Meisel said “We're already able to have a conversation with the technology to some degree”.

Main Article:
http://www.cnn.com/2010/TECH/03/19/voice.recognition/index.html

Second Article:
http://www.hitl.washington.edu/scivw/EVE/I.D.2.d.VoiceRecognition.html