Smart Speakers: Audio Design Rules for Voice-Enabled Devices

Because every R&D department in the planet is currently looking at implementing voice, and everyone's looking at audioXpress for guidance on how to design a smart speaker, in this edition Kevin Connor, shares his insider knowledge on the topic. Connor, a Cirrus Logic engineer, explains how to provide audio and voice solutions, and design products that sound great and respond reliably to voice commands, regardless of backend service. This article was originally published in audioXpress, January 2018.

Google is all-in in its determination to compete with Amazon, Apple and everyone else on the hardware front. On the same day, Google unveiled its second-generation family of consumer hardware products, including new Pixel 2 smartphones, Google Home Mini and Max smart speakers, an all-new Pixelbook tablet/laptop, Google Pixel Buds wireless earbuds, and more. No longer releasing "reference hardware" for its software ecosystem, Google is apparently determined to emulate Apple's successful strategy.

In previous editorials, I have highlighted the important role of smart speakers in promoting the user case for voice personal assistants (VPAs) and voice recognition applications - given the ideal combination of far-field microphone arrays with a complete audio ecosystem that encompasses digital signal processing, acoustic echo cancelation, noise cancellation, and many other technologies. This opens significant opportunities for the audio industry, given we understand the challenges.

Futuresource Consulting has just released its most recent consumer electronics report covering a new place for audio in the smart home. “Voice recognition technology is shaking up the CE industry, broadening the horizons of speaker vendors and reinventing the audio device as the gatekeeper of voice, smart home and machine learning,” the report says. Futuresource research forecasts important growth in audio applications for the connected home.