The Aaware Sound Capture Platform integrates algorithmic acceleration technology and a flexible microphone array board with the hardware power of Avnet’s MiniZed Zynq SoC development and demonstration platform, using dual-core Xilinx Zynq-7000 All Programmable SoC devices.
“Leveraging the utility and expandability of Avnet’s MiniZed platform, Aaware’s Acoustically Aware sound capture algorithms enable product development teams to create far-field, voice-to-machine communications functionality that is more natural and robust than anything I have seen on the market today,” says Jim Beneke, vice president, engineering and technology, Avnet. “This versatile technology not only solves the problem of canceling noise, echo and reverb that often confuse many popular cloud-based digital assistants and robotics applications, but the ability to recognize more than one wake word/phrase is a true differentiator.”
“Avnet is a top-notch distributor that has cultivated an exceptionally collaborative relationship with Xilinx, whose technology is consistently at the core of next-generation applications and solutions,” says Joe Gianelli, CEO and co-founder of Aaware. “Working with Avnet, and by extension Xilinx, will enable Aaware to reach a greater array of customers and markets worldwide, delivering world-class audio sound capture solutions that can help them bring more robust AI applications to market quickly and effectively.”
Aaware’s Acoustically Aware sound capture algorithms, paired with TrulyHandsfree wake word detection technology from Sensory, allow systems to adapt to differing noise interference, without requiring calibration for different environments or integration of the reference signal.
“By integrating Sensory’s industry leading wake word detection with Aaware’s noise processing, device makers are able to deploy powerful products that feature always-listening speech recognition capabilities that thrive in noisy environments,” says Bill Teasley, vice president of engineering at Sensory.
“Providing customers with scale and flexibility, coupled with powerful edge acceleration for the voice-enabled Artificial Intelligence (AI) application market, is compelling,” adds Yousef Khalilollahi, vice president, core vertical markets, Xilinx. “We see tremendous opportunity accelerating at the edge with Xilinx All Programmable SoCs and Aaware technology, enabling voice assistants, robotics and other AI-related applications.”
Unlike standard sound capture platforms which typically offer only fixed microphone array configurations, the Aaware platform has a concentric circular array of 13 microphones that may be configured in different combinations, allowing for product performance tuning. The Aaware platform separates source speech (wake word) and follow-on speech from interfering noise with ultra-low distortion, allowing the system to more easily integrate with third-party speech and natural language engines. In addition, source localization data can be forwarded to downstream applications, such as video, improving the performance of sophisticated multi-sensor AI applications, including those for industrial robotics and surveillance.
Avnet and Aaware are demonstrating the new voice interface technology at CES 2018, January 9-12 in Las Vegas, Eureka Park booth #50212 in the Sands Expo.
www.minized.org/product/AEV13MZ
www.aaware.com
