As the TribalScale team ramped up for Toronto’s Amazon Echo Hackathon, we prepared for our first foray in the world of voice user interfaces(VUI). Coming from a mobile background, with a mindset for touch user experience, this was a whole new interaction model.
The Amazon Echo is a voice controlled device that interacts with the Alexa Voice Service. The device is a smart array of microphones, which when paired with cloud technology, becomes an immensely powerful piece of technology. Alexa is the virtual assistant, developed by Amazon with a VUI, to help users interact with devices using only their voice. Alexa utilizes cloud processing on Amazon Web Services to perform Machine Learning, AI and Natural Language processing.
In preparation for the hackathon, our team chose to focus on use cases in which a VUI would offer a more organic experience than a touch screen. From there, our winning app, ‘My Fridge’, came to life. Our application keeps track of your fridge’s contents, including amounts, and expiration dates based on information that you feed the VUI through natural discussion. Further, Alexa can suggest recipes based on the ingredients you have and their freshness.
The Challenges of VUI
A mobile application can display functionality through menus and text suggestions. A VUI poses a challenge when attempting to convey the scope of functionality to a user. When the VUI requires a large amount of information in the response, dictation can be time consuming. To solve this issue, we utilized the ability to push a card of text to the Amazon Alexa App. This worked well for recipes, where Alexa dictating the entire recipe would be hard to follow.
A current drawback for echo, which would be interesting to explore, is the lack of voice fingerprinting to identify users. This feature, along with increased security, could allow user specific interactions without the need to manually swap accounts.
The Future of VUI
Alexa and her VUI counterparts have a vastly broad spectrum of applications. In the healthcare industry, Alexa offers the ability for doctors and dentists to dictate information to the Echo which can be stored and utilized later. Alexa can then be used to sort through or analyze massive amounts of data to instantly allow hands-free interaction during procedures. The connected car experience is another obvious application for VUI. The ability to dictate and remain hands-free will continue to add better, faster and safer functionality across a wide array of industries.
As our teams at TribalScale continue to push the boundaries of IoT capabilities, we highly anticipate leveraging voice user interfaces as a common integration. To date, our experiences have been dictated by touch capabilities for the majority of our interaction with devices. The possibility of high-functioning voice user interfaces will push the boundaries of current development capabilities. As with many opportunities, VUI will pose a multitude of challenges.