I still work in the pharmacy on occasion. It keeps me up to date with changes that I’ve made to various pharmacy systems and gives me the opportunity to make sure my pharmacist skills haven’t evaporated. One thing it doesn’t do is get me away from my current technology related duties. In fact it puts me closer to the action and even more accessible to pretty much everyone, which means I spend a majority of my “staffing” time dealing with things related to our automation; carousel picks and loads, packager fills, compunder checking, labeler input and checking, minor troubleshooting, etc. It’s not that someone else can’t do it, but that’s the way it works out.
Anyway, during one of my staffing days last week I found myself spending a lot of time around our AutoCarousels and AutoPack machine. The technicians had an unusual number of items to package in addition to a fair number of new items to teach to the AutoPharm formulary. After my umtenth time logging into the packager, it dawned on me that speech recognition would be a great thing to have; no keyboard, no mouse, just me talking to the machine. I wouldn’t need a password because it would recognize my voice.
Speech recognition isn’t an exotic idea. It comes standard with Windows Vista, and from what I’ve read works pretty well. It’s not even new to healthcare as a quick Google search revealed speech-enabled EMRs.
Speech recognition is based on a statistical approach that provides the probability of a given word sequence. The computer turns your voice into a stream of digital data and compares the signals to words in its dictionary, which is a database of commonly used words found in the English language. It’s not perfect, but it sure is neat.
Wouldn’t it be nice to walk up to my AutoPack and say “fill-sevelamer-800mg- tablets-quantity-fifty” and simply walk away? I think so. We could even give the packager a cool voice to answer with. How about a pirate: “Yarr matey, packagin’ fifty, 800mg sevelamer tablets. Argh.” Or maybe the voice of HAL from 2001 A Space Odyssey: “Good morning, Jerry. Initializing packaging sequence. Your sevelamer tablets will be available in approximately 2 minutes, 36 seconds.” Now, that would be cool. If only.
Hi Jerry,
I live the idea of pirate voice for the Autopack. How about a YODA mode also “barcoded packets now I will make”. Also, I can see the HAL voice saying “I just can’t do that Jerry, the lot has been recalled.” Hmmm, let me talk to Product Management.
That’s too funny. I see your point about HAL, he can be a little obstinate at times. YODA is a good call though. He has a can do attitude -”Do or do not. There is no try.“
[...] – GigaOM: “Microsoft once again is touting its speech-recognition technology, predicting on its site this week that “talking to a computer may soon be as natural as using a mouse.” But while voice is a natural fit for mobile phones and some other platforms, when it comes to traditional computing — using a laptop, desktop or even a netbook — the use-case scenarios for speech recognition are more limited. It will take quite an effort to convince users to talk to their laptops instead of typing on them.”- I disagree, I think there are some practical uses for speech-recognition. Like any new technology it must be modeled into something you want. My thoughts on subject can be found here. [...]
[...] is an interesting notion. It’s nothing new and I’ve blogged about the possible uses of speech recognition and facial recognition in the past. Many facilities utilize basic forms of biometric [...]