XMOS VocalFusion 2-Mic Dev Kit for Alexa Voice Service Qualified by Amazon

Amazon has qualified the VocalFusion 2-mic dev kit for Alexa Voice Services launched by XMOS for smart TVs and set-top boxes in July 2019. The qualification highlights the opportunity for manufacturers to build Amazon Alexa voice capabilities into their products more easily and cost effectively than ever before. Amazon highlights the product’s engineering innovation, enabling lower cost voice capabilities with all the performance of a 4-mic solution, and paving the way for mass market implementation of far-field applications.
The XMOS development kit, which is based on the XMOS XVF3510 voice processor, is a BOM-efficient solution built for modern living spaces. The product’s next-generation acoustic algorithms create a compelling, premium experience with far-field voice control, opening the door to a more natural conversation with technology.

The development kit includes the XVF3510 processor base board with Micro-USB connector for power and USB device connectivity, low jitter, audio quality clock, line-in port, xTAG interface for JTAG debug, and dual microphone array daughter board. The system uses two Infineon IM69D130 PDM (Pulse Density Modulation) MEMS microphones with 71mm inter-mic spacing. A Raspberry Pi HAT adapter board provides additional I2S audio and I2C connectivity, a 24-bit stereo DAC, and 4 user controlled buttons and 2 LEDs. The solution requires a Raspberry Pi 3 board to run the AVS SDK and Sensory TrulyHandsfree wake-word engine.

The XVF3510 voice processor supports full duplex stereo acoustic echo cancellation (AEC), barge-in, with Interference Canceller, Noise Suppression, Automatic Delay Estimator Control (ADEC), and Automatic Gain Control (AGC). The Interference Canceller nulls point noise to cancel out typical noise in the soundscape, Stereo Acoustic Echo Cancellation suppresses unwanted speaker echo and enables barge-in across audio playing from the device, while noise suppression removes background noise from other devices. The solution also features Automatic Delay Estimator to adjust the audio reference signal latency dynamically, ensuring the Acoustic Echo Cancellation algorithms deliver a smooth, real-time barge-in experience.

“Amazon is seen by many experts and consumers as the leader in the world of voice, and our engineering expertise will be helping to transform the way consumers interact with everyday devices like TVs. This qualification from Amazon is a real endorsement for the VocalFusion 2-mic dev kit and the XMOS brand,” says Mark Lippett, president and CEO at XMOS.

The XMOS XVF3510 voice processor is available at a market-leading cost of $0.99 on orders over one million units a year.
www.xmos.com/products/voice/amazon