Voice User Interface (VUI) is what makes a programmed machine, like your TV, smart heating device and good old voice assistants like Alexa, Google and Siri, able to respond to your voice command. And as the technology becomes more sophisticated, we’re seeing rapid adoption in all sorts of weird and wonderful areas of our lives; from Artificial Intelligence (AI) powered health service voice assistants and voice biometrics in banking, to “voice shopping” and even under the guise of providing extra parental help in children’s bedrooms.
It’s time to sit up and take notice of our computers. Forget the futuristic headlines about crypto currency, self-driving cars and AI robots, voice recognition tech is the future. Just seeing the world’s tech giants clamouring to lead the market on voice-enabled devices tells us that; which inevitably makes us think about the exciting prospects for it, as well as raises some ominous concerns about our privacy too.
Talking to machines: A work in progress
The funny thing is, even though voice recognition technology feels relatively new to most of us, it actually has a rich history dating back to the mid-20th-century.
And yet, saying that, I do remember my friends calling it a “sci-fi dream” when I wished for some sort of reliable voice dictation in the days of writing my university dissertation in the early 2000s. So, given that timeline, it still makes sense that most reports of voice UI as mainstream tech only really started in the post-2011 Age of Apple’s now ubiquitous personal assistant, Siri.
As my family love to remind me, a long time has passed since then, and amazingly, my day-to-day life is now punctuated with talking to machines. I never would have thought it 20 years ago, but it feels perfectly natural to talk to a computer to make “hands-free” adjustments to the entertainment or navigation in my car, or to make calls on the go, or simply to search for the answer to a question by asking my computerised assistant. It’s pretty mad when you think about the technological evolution in only a couple of decades; which, incidentally, was brought home to me when I recently surprised myself by replying to a WhatsApp message with voice recording! ?
My voice recognition productivity hacks at work
Beyond the familiar entertainment and personal “connected home” uses, I’ve recently discovered massive productivity benefits of using voice recognition tech at work. My process for scheduling meetings and setting up reminders is now to ask Google to do it for me. And it goes without saying that if I need to search for something, that I revert to doing a voice search first.
My newest and favourite voice command productivity hack, is using the built-in recorder app on my Google Pixel phone. (Thanks to Matt Debouge for introducing me to it!) The recorder automatically transcribes speech to text at the press of a button, which I’ve found really powerful for note-taking, not least because it’s so much faster than using the Rocketbook “smart notebook” that has been my typical “go to” for meetings over the last couple of years. On top of that, being able to edit the recordings is a mind-blowing feature that is opening up a new world of opportunities and ideas for how I can use (and share) my notes in future too.
Voice recognition at my PC
I’m still most productive at work when I’m sitting in front of my PC, and particularly when it comes to writing, when I have the keyboard at my fingers. But saying that, I am finding there is a place for speech-to-text there too. I’ve found Google Docs’ voice typing feature easy to use, and Microsoft Word’s “Dictate” button just as innovative. So, depending on what I’m working on, or for who, I am familiar with using both to help me make first drafts of anything from articles and blogs to reports and social media posts.
I’ve found the hardest part has been getting used to the voice commands for basic actions and punctuation, but as I’m still working on that, I thought I’d share a few here that I wish I’d known before, that should help you…
Essential commands for writing with your voice
Here are some basic commands for Google Docs and Microsoft Word speech recognition:
To do this | Say this in Google Docs | Say this in Microsoft Word |
Insert a new paragraph | New paragraph, Insert sentence, Add new para, Add paragraph, New line | Next line |
Delete the typed text | Clear everything, Delete all text, Remove everything | Delete |
Here are some punctuation commands for Google Docs and Microsoft Word speech recognition:
To insert this | Say this in Google Docs | Say this in Microsoft Word |
. | Full stop, dot, point, period | Full stop, period |
, | Comma | Comma |
? | Question mark | Question mark |
! | Exclamation mark, exclamation point | Exclamation mark, exclamation point |
: | Colon | Colon |
And for anyone wanting to delve a little deeper, here are some videos to help you get started with these tools…
Video example of voice typing in Google Docs