DSP Group has been quietly amassing a number of design wins for its voice processors, including inclusion in the Samsung A8/8+ and Gear Sport devices, Go Pro 6 camera, Ultimate Ears’ Blast and Megablast smart speakers, as well as devices from Pioneer, Fujitsu and Onkyo.
Now, the company is partnering with the biggest maker of smart home speakers in Amazon with its HDClear 3-Mic Development Kit for Alexa Voice Service (AVS) to help developers build Alexa-powered smart speakers, wearables, remote controls and other smart home devices without a drain to the battery.
The kit includes a printed circuit board with the DSP Group’s DBMD5 audio processor, a Raspberry Pi and 3-microphone array as well as pre-process noise-reduction, beam-forming and acoustic echo cancellation (AEC) algorithms for enhanced voice accuracy. The audio front end kit allows for low-power wake-on-voice operation and far-field voice recognition performance with only three microphones.
DSP Research is banking on the growth of the smart speaker/voice assistant devices in the coming years as Juniper Research forecasted that 870 million devices will be in operation by 2022.
“The migration toward voice user interfaces marks a sea-change in users’ interactions with electronic devices,” said Ofer Elyakim, CEO, DSP Group. “Working with Amazon is a vital step forward in our steady expansion into voice user interface technologies. OEMs and ODMs can literally pick up our development kit, plug it in and begin using it to create richly featured acoustic front-ends for Amazon AVS devices — while conserving precious board space and battery life.”
The self-contained audio processing kit uses DSP Group’s HDClear voice enhancement signal processing algorithms, first-stage wake word engine and low-power voice activity detector with a DSP chip. Three power operating modes are included; a low-power 1-mic voice trigger mode; a 3-mic noise reduction mode with beam-forming and noise reduction; and a 3-mic barge-in mode with AEC processing.