Uniquely, the solution also supports configurable AEC latency, where the AEC reference signals can be accurately calibrated, and the latency adjusted, to enable after-market far-field voice accessories for existing consumer electronics products.
Commenting on the announcement, Mark Lippett, President and CEO at XMOS says, “This device and evaluation kit will fuel further growth in the integration of embedded voice controlled devices at the edges of our rooms, particularly those used for high quality music and TV control. We are looking forward to showing this solution at CES in Las Vegas next month. We already have the most comprehensive portfolio of far-field voice capture solutions, and this announcement further consolidates that position.”
As with all other XMOS voice solutions, commands are accurately captured from across the room for processing by a cloud-based speech recognition system, even in complex acoustic environments. The XVF3500 voice processor delivers sophisticated voice digital signal processing (DSP) 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 an adaptive beamformer that follows a speaker. Additional sophisticated dereverberation, automatic gain control, and noise suppression provide crystal clear voice interaction experiences even in noisy environments.
During CES, XMOS will be at The Palazzo Hotel, Las Vegas, 9th -12th January 2018. They will showcase their new stereo-AEC solution, the existing VocalFusion 4-Mic kit for Amazon AVS, VocalFusion speaker with linear and circular arrays, far-field voice processing commercial deployments, and human machine interface developments.