Aaware, Inc. Acoustically Aware AEV13MZ Far Field Voice Product Brief Development Platform Platform Overview Key Features & Benets The Aaware far eld voice development Complete source localization, separation, platform provides a complete single-chip and far-eld voice multi-wake word voice and sound capture solution detection for voice assistant applications focused on applications where strong Interference cancellation of nearby interfering sources and high ambient sources without a reference noise are present. Low distortion separation for supporting multiple 3rd party speech recognition and The Aaware sound capture algorithms natural language processing include source localization, proprietary Flexible microphone support of 1D/2D spatial/spectral/temporal source non-uniform arrays separation, and noise suppression to Source localization detects direction deliver low distortion audio of acoustic Optional multi-channel AEC available sources in the sound eld. Up to a 16 Integrated multi-wake word detection microphone array, including non-uniform (*Sensory) Default: Alexa, OK Google 1D and 2D arrays, in end-re or broad- Single-chip solution with Dual ARM-A9 side congurations, are supported. 1D cores, 512MB Memory, 8GB eMMC, and 2D source localization is supported Ubuntu Linux, WiFi, and Bluetooth depending on array choice. The Aaware s o u n d c a p t u r e a l g o r i t h m s a r e accelerated in FPGA hardware optimizing performance, software Platform Block Diagram footprint, cost, and power. The AEV13MZ platform leverages up to 13-microphones with integrated Sensory multi-wake word for robust voice assistant applications in the presence of strong direct or ambient noise with low distortion, allowing for better integration with third party speech and natural language technologies. The Aaware technology is always on, captures the speaker as they move, and cancels multiple noise sources without needing the reference audio, making it a very exible t for any product that anticipates strong interfering noise sources. 2018 Aaware, Inc. All Rights Reserved Aaware, Inc. CondentialThe Aaware platform uses a single-chip AEV13MZ Platform Specications solution integrating the Aaware source separation algorithms and a dual-core ARM-A9 applications processor with embedded Ubuntu Linux. Voice application developers can immediately start developing voice applications based on wake word audio and/or noise/interference suppressed audio coming from a dened direction. A standard Ubuntu Linux e n v i r o n m e n t p r o v i d e s f a m i l i a r development tools from broadly available repositories. Aaware sound capture algorithms can be customized for different 1D/2D non- uniform arrays to match your products physical constraints, and also xed spatial z o n e s w h e r e t a r g e t s o u n d s a n d interferences are known and stationary. Acoustic Echo Cancellation (AEC) is also available. Please contact your Aaware representative for more information. The AEV13MZ far eld development platform is ready to use out of the box, with 1994-2018 Sensory Inc. All rights reserved * a Linux ALSA based audio interface, ** 2018 Avnet Inc. All rights reserved making it immediately software ready. *** 2018, STMicroelectronics, All Rights Reserved www.aaware.com 20 S. Santa Cruz Ave, Suit 300 info aaware.com Los Gatos, CA 95030 2018 Aaware, Inc. All Rights Reserved Aaware, Inc. Condential