PC World cites speech recognition as one of Microsoft’s big weaknesses. The article states that there have been significant advances in the equipment used to record audio and store audio but the actual deciphering of audio is still behind.  

The author actually tested the dictation feature by reading aloud the article he wrote.  This was his experience with the amount of errors produced.  “A 95.0% accuracy rate would mean you’d have to correct more than fifty mistakes. That gets old fast.”  We definitely cannot work with a 95% accuracy rate when we handle audio for physician’s charts.  

Microsoft contacted the author and explained that they are working towards integrating their range of devices and experiences.  It is definitely not something that is going to change in the next few months.

Until technology can catch up, iScribes will continue to use humans to decipher audio for physician’s charts.  You can learn more about us here.

Source: PC World


Comments are closed.