VUI – Voice User Interface, is the audio equivalent of GUI ( graphical user interface = visual). VUI uses voice commands, giving us a conversational and hands-free experience. We have been using IVR for a long time, especially call centers (press or say 1 for location…) And remember the Clapper? (Clap on, Clap off, THE CLAPPER!) I used one for a long time, it wasn’t the most technical piece of equipment, but it was practical for me. Today I can ask my Echo to control multiple lights with having to clap my hands. And it is the best when you are elbow deep in the kitchen and need to set a timer.
Growing up int he 70s we changed the TV channel by getting up from the couch and twisting a dial on the TV set. Soon we had remotes controls (aka ‘the clicker’ – because of the clicking sound it made with the buttons). Today, you can opt for a voice controlled TV. A simple shout and the TV will turn on, off, or the change the channel.
It’s fascinating when we can turn hardware into software.
The other night I went to a UX presentation on VUI. With today’s technology the capabilities and functionalities for voice assistance are constantly developing new use cases.
VUI also called voice assistance or intelligent voice agent relays on speech recognition technology to provide a high confidence factor in understanding the ‘intent of the request’ from the speaker. Programs weed out the ‘ums and hums’ and other unnecessary words from the speaker.
Always-on allow the devices to respond when give a wake word or prompt. For my Echo (brand) device, the wake word is defaulted to Alexa (name).
Are you wondering about big brother, fraud or hacking? Like any other data points or apps that you use, there are security factors to be aware of.
First, VUI devices are ‘always-on’, this allows for the device to respond when necessary. But because it has the ability to listen – if someone was looking for a back door this could be it (remember when baby monitors were new). Keep your router and Wi-Fi secure, this will help eliminate intruders.
Second these devices create, collect and store your history data. Each request is captured similar to your browser search history and click thought and saved on cloud-based storage systems.
In both security cases, a warrant is needed before a government agency may request to listen in or see your history files from these VUI providers. It is similar to a request for a mobile phone call history. (To date – Feb 2017 – Amazon has not released any access of anyone’s Echo to the government.)
Another always-on device is Google Home. Applications such as Siri and Comcast’s voice remote control require you press a button to start the commands. Highlighting the hands-free benefit of always-on.
A ‘skill’ is a command using human voice to communicate. Echo recently released its open API at CES 2017 – it now has over 10,000 skills. By having an open API, it allows any developer to create skills that can integrate with other electronic devices. Like shouting from your bed to have Alexa to start brewing your coffee.
Next on the horizon is biometric voice identification. This voice recognition can distinguish who is talking or making the request. So when I say ‘play my favorite song’ it knows the difference between my favorite song and yours based on who gave the request.