My next stop on the dev-kit tour brought me to a meeting with my old friend Alexa. The kit was from Conexant, and it allowed me to build a voice-enabled interface, a la Alexa. This one was a little trickier than the others in that I had to source many of the components. I was able to make use of the Raspberry Pi from a previous project, but I needed to get some cables, a wired mouse and keyboard, and a speaker from Amazon. I know, life’s tough. It’s just that most of the kits are shipped fully inclusive, meaning that you get everything you need to get up and running.
The kit is dubbed the DS20921AudioSmart 2-Mic Development Kit for Amazon AVS. It’s built with Conexant’s dual-microphone voice processing IC, the CX20921. The device does an excellent job of eliminating most of the environmental concerns a developer might have, like echo cancellation, background noise, microphone position, and speaker placement.
Once I had all the components I needed and got everything connected, the first step was to download and install the Raspbian Jessie operating system onto the Pi, which was done by downloading NOOBS, which stands for New Out Of Box Software. It’s actually a great tool to install an OS onto the Pi. Step two was to register for a developer account on Amazon. I could have sworn I had done this in the past, but alas, I couldn’t find my credentials so it was easier to simply start from scratch. Then the fun began.
I registered my product/project and got down to work. Conexant made it pretty easy by offering lots of sample code and a step-by-step process. I’m happy to report that I made it through the entire process with nary a call to tech support. Upon completion, I had my own working (sort of) Echo-like product. Some simple testing proved that it worked as expected from a decent distance (across a fairly large room) and even when I had music or a television playing in the background.
The next step for me, when free time avails itself, is to integrate the hardware into some other device to make it more useful, as you would with a real end product. I could easily see how you could add it to pretty much any appliance for hands-free operation. When you get into large volumes, the price comes way down. And depending on the intended target, you could already have some of the necessary hardware in place (like the power components, mikes, speakers, etc.).
The bottom line is that once you get yourself going, it’s a fairly straightforward process to build voice control into any hardware that you desire. Order a kit from Arrow. It sells for $299.
About the Author
Richard Nass is the Executive Vice-President of OpenSystems Media. His key responsibilities include setting the direction for all aspects of OpenSystems Media’s Embedded and IoT product portfolios, including web sites, e-newsletters, print and digital magazines, and various other digital and print activities. He was instrumental in developing the company's on-line educational portal, Embedded University. Previously, Nass was the Brand Director for UBM’s award-winning Design News property. Prior to that, he led the content team for UBM Canon’s Medical Devices Group, as well all custom properties and events in the U.S., Europe, and Asia. Nass has been in the engineering OEM industry for more than 25 years. In prior stints, he led the Content Team at EE Times, handling the Embedded and Custom groups and the TechOnline DesignLine network of design engineering web sites. Nass holds a BSEE degree from the New Jersey Institute of Technology.Follow on Twitter More Content by Rich Nass