There is a new development speech tool for those with disabilities or repetitive strain injury to use Mouse as Nuance Communications released Dragon Naturally Speaking 9, a new version of PC-based speech-recognition technology which is 20% more accurate than its version 8.
The new version is in development for the last 2 years. It is more accurate than its earlier version and hence provides a better tool to write on PC through speech. According to the company, the new version have 99% dictation accuracy which will help people with disabilities or strain injury to voice their PC commands instead of using a Mouse.
“People who tried it three, four, five years ago will notice massive improvements,” said Matt Revis, Nuance’s director of product management for dictation solutions.
One more good point is that people can begin using the speech software without training the program to understand their voice. Instead, the software will learn as it goes.
“Within several uses, the software catches up. It learns as you correct it.”
Nuance’s update comes as Microsoft tests its own speech recognition technology, which the software giant plans to offer at no charge within its new operating system, Vista.
Microsoft is also concerned for accuracy of the program. It recognizes confusing words like “cake” from “bake” according to the context of the sentence. Along with, it is also working on providing an interactive user interface so it’s easier for average people to command the software to fix errors or to switch applications.
Microsoft’s Chambers said, “At one point in the future, we believe that the speech recognizer will be more accurate than a human is. We already do that in numerical digits.”
“The technology is really becoming more mature. The accuracy continues to improve at an exponential rate,” Microsoft software architect Rob Chambers said.
Speech recognition needs accuracy and it is hard to implement. External noise, speakers high pitch voice are some of the common factors that can affect the program’s reception of the speaker’s voice and cause it to misinterpret language. For highest accuracy the software must learn the nuances of an individual’s speech patterns.