What Makes Us Different
- Robust noise/echo/reverb cancellation without reference
- Lower ASR word error rate due to ultra low distortion source separation
- Flexible algorithm – supports non-uniform microphone arrays
- Scalable microphone array optimized for your product
- Scalable HW/SW implementation with Xilinx Zynq®
- Complete Ubuntu based Linux development platform – software ready
Sound Capture Technology
Noise & Echo Cancellation
Other technologies tout their ability to cancel noise and echo from their own speaker. This is easier to do as you have access to the interfering reference signal. At Aaware, we go beyond traditional AEC and cancel interfering noise were we don’t have the reference signal. This is much more difficult but gives our customers the ability to integrate without needing the interfering reference signal to adequately cancel enough noise to enable superior far field voice interfaces.
Source Detection & Localization
Detecting and localizing sources in the sound field is a critical step in finding what you’re looking for. The Aaware technology not only localizes and detects omni directionally, but separates the source speech (wake word + follow on speech) with ultra-low distortion which allows us to more easily integrate with other third party speech and natural language engines, such as with Amazon Voice Services, Google Assistant, and Sensory’s Truly Natural. We also forward source localization data to down stream applications, such as video.
We set out to solve the problem of canceling noise, echo and reverb and to attain the best performing far field voice interface while not being constrained to just a few microphones and a software only implementation. This led us to the amazing benefits of algorithmic acceleration leveraging the power of FPGA hardware. In doing so, we provide our customers with the best possible price/performance and all integrated into one fully programmable SoC.
Flexible & Scalable Algorithm
Our algorithm was architected such that it can easily be re-configured to support up to 13 microphones, with the current development platform, and to support non uniform array sizes. Product teams aren’t stuck with a rigid microphone configuration and don’t have to upgrade to larger implementations or components just to add a few microphones, making this a flexible fit with products in many markets.