The “Barrier Trifecta” of Voice Dictation
Voice dictation/recognition has been an interest of mine since the mid 90s. From years of playing the piano as well as composing every school paper on a PC, my words per minute using a keyboard is actually quite fast. However, the appeal of being able to translate my thoughts via natural speech to text has still been a passion of mine.
Voice dictation has come of age – but it has not always been so. Interestingly, the challenges to voice recognition parallels the same challenges for digital photography.
The challenges represent barriers which I will call the Barrier Trifecta. They are: pervasive access, resolution, and processing power.
Pervasive access
For cameras, the cliché answer to the question of “which is the best camera” is, “the one you have with you at the time”. Obviously, the specs of the camera are irrelevant if the camera isn’t available to take the picture at all. In voice recognition, this was one of the biggest problems. In the past, quality of voice recognition was limited to high fidelity microphones almost exclusively dedicated to an office environment. Which meant that the time and place for voice dictation had to be carefully chosen, and scheduled for when you were at your desk. Years ago, I tried working around that limitation once by configuring a laptop in my car so that I could dictate while battling Atlanta traffic. Poor results.
Resolution
We all remember the grainy, low fidelity photos of our first camera phones. Sometimes it was difficult to make out all the people in the photo. “Wait; is that a picture of Bigfoot?” Oh no that is just Uncle John? Voice recognition suffered from the same problems. Lack of noise cancellation, and poor microphones created scenarios where the error rate for voice dictation was still too high. “Hire Mary” vs “Fire Larry” sound the same but have radically different outcomes. Especially for Larry.
Processing power
We are in inpatient bunch and our voice dictation train of thought is easily derailed, especially if technology forces an unnatural cadence. Our digital cameras have suffered similar challenges. How many times did you lose that perfect moment because the device wasn’t ready for you to take that Pulitzer Prize photo.
Deliver Voice Dictation to any Enterprise Application
The barrier trifecta for mobile devices has been largely overcome, both for cameras and for voice recognition/dictation. The multiple noise cancellation microphones along with the innovative processing of human voice leads to astounding accuracy. That is why we are so excited about the new technology we released in version 4 of 2Go™ .
We are ecstatic to deliver voice dictation into any enterprise application. Yes, every enterprise application. Yes, even that old one you’re thinking about right now. Yep, the one that keeps you chained to your desk.
Have you ever wanted to dictate into that old ERP application at 300 words per minute from your phone while waiting for the plane? How about entering detailed notes in a sales order or in that CRM application? 2Go™ delivers this to all users with any application it is connected to.
Using 2Go™ voice dictation with your enterprise applications may allow you to be so mobile and efficient that you really do have time to get that Pulitzer Prize photo of Bigfoot and not just Uncle John.
