XMOS delivers first Amazon Alexa Voice Service development kit with linear mic array for far-field voice capture

XMOS Ltd (www.xmos.com), a leading supplier of advanced embedded voice and audio solutions to the consumer electronics market, today announced its VocalFusion 4-Mic Dev Kit for Amazon Alexa Voice Service (AVS) is the first far-field linear mic array solution available. The XMOS kit is ideal for developers who want to integrate Alexa into smart panels, kitchen appliances, and other commercial and industrial electronics.

The kit features a compact four-microphone linear 100mm array. The captured voice signals are crystal clear even in noisy environments, enabling commands to be accurately captured from across the room for processing by the Alexa cloud-based speech recognition system. XMOS is the only solution to date that packs audio digital signal processing (DSP) and programmable I/O processing and control software into a single chip, enabling customers to significantly reduce their bill of materials, flexibly tailor their designs, and reduce costs.

The VocalFusion 4-Mic Dev Kit for Amazon AVS is the first development kit to feature a reference client built using the recently released AVS Device SDK. The AVS Device SDK is designed to further simplify the experience of creating Alexa-enabled products, thereby helping commercial device makers get AVS products to market faster.

“We’re delighted to work with XMOS as they introduce the first far-field linear mic array AVS solution, making it easier for developers and OEMs to build Alexa-enabled products,” said Priya Abani, Director, Amazon Alexa. “XMOS’ VocalFusion 4-Mic Dev Kit for Amazon AVS will accelerate the deployment of Alexa in deeply embedded systems, new device types, and form-factors, bringing customers more choice of where to access Alexa.”

At the heart of the XMOS solution is the VocalFusion XVF3000, a highly integrated far-field voice processor based on the XMOS award-winning xCORE multicore architecture. The XVF3000 delivers sophisticated voice DSP capability including a full duplex acoustic echo canceller (AEC) with barge-in capability that enables users to interrupt or pause a device that’s playing music, and sophisticated noise suppression with adaptive beamforming to provide high quality voice interaction experiences even in noisy environments.

“We’re excited to collaborate with Amazon, the pioneer in voice-enabled consumer solutions. We believe that our homes and offices will very soon be smart environments, and that voice provides the most convenient and intuitive solution to control the many machines that surround us,” said Mark Lippett, President and CEO at XMOS. “Solutions like ours enable developers to bring to market connected products that can be used with simplicity, in our own natural spoken language. We are working with our partners to accelerate the adoption of AVS as the voice solution of choice for the Internet of Things.”