The dev kit was unveiled at the world's largest voice event - the Voice Summit - being held in New Jersey, in the US.
It is based on the XMOS XVF3510 voice processor, enabling manufacturers to embed a voice interface into mass-market smart TVs and set-top boxes - and to do so economically.
Developed in the UK and purpose-built for modern living spaces, XMOS’ next generation acoustic algorithms produce a much improved experience in far-field voice control, opening the door to a more natural conversation with technology.
Designed to work intelligently by analysing the acoustic environment, the XMOS technology identifies and isolates a voice command from every other sound in the room (including any media streaming through the device itself), enabling far-field voice capture with close range precision.
The XMOS algorithms include:
A Stereo Acoustic Echo Canceller: Suppresses unwanted speaker echo and enables barge-in
An Interference Canceller: Nulls point noise sources to cancel out unwanted background noise.]
An Adaptive Delay Estimator, which dynamically adjusts audio reference signal latency, ensuring the Acoustic Echo Cancellation algorithms deliver a smooth, real-time experience.
“The recent uptake and demand for devices featuring voice assistants has continued to surge”, said Simon Bryant, Research Director at Futuresource Consulting. “The strong adoption in multimedia and entertainment is expected to continue and this new device from XMOS addresses what manufacturers who want to add far-field voice control to their product lines will be looking for.”
“Giving people the freedom to control the TV with their voice from anywhere in the room, is a more natural experience - you simply tell your TV what you want to watch.” said Mark Lippett, CEO, XMOS. “Our new far-field voice processor gives developers an easy to implement solution, at a very compelling price.”
