Microsemi Corporation (Nasdaq: MSCC), a leading provider of semiconductor solutions differentiated by power, security, reliability and performance, today announced its AcuEdge Development Kit for Amazon Alexa Voice Service (AVS). The Microsemi AcuEdge Development Kit for Amazon AVS delivers enhanced audio processing to improve voice recognition rates in adverse audio environments for emerging human to machine (H2M) applications in the internet of things (IoT), industrial internet of things (IIoT) and automated assistance markets.
The kit is designed to enable third party developers and original design manufacturers (ODMs) to evaluate and incorporate Alexa functionality in H2M applications, while interfacing with the Microsemi Timberwolf ZL38063 multi-mic audio processor.
Microsemi’s Timberwolf is a field programmable, field upgradable digital signal processor equipped with specific hardware accelerators to run three simultaneous acoustic echo cancellers (AECs). Its AcuEdge Development Kit for Amazon AVS comes complete with a development board that connects directly to a Raspberry Pi and plastic frames to help position microphones and speakers in targeted applications. It also enables users to speed development of their products by utilizing the quick start guide and user interface.
“The Microsemi AcuEdge Development Kit for Amazon AVS offers a scalable platform enabling developers to quickly and cost effectively achieve their design criteria requiring two mics,” said Shahin Sadeghi, marketing director at Microsemi. “Our AcuEdge development kit utilizes Microsemi’s state-of-the-art Timberwolf solution and has been tested for compatibility with Amazon AVS. The kit is for use by ODMs and third party developers to bring innovative H2M applications to market.”
Microsemi’s Timberwolf is enabled with compressor/limiter/expander (CLE) microphone pickup algorithms, beam forming, and stationary and non-stationary noise reduction, enabling voice control and speech recognition not only from a distance but also in the presence of adverse noise and audio sounds. The complete kit features a Timberwolf evaluation board, which is populated with two microphones capable of operating in both 180 degree and 360 degree audio pickup modes. The evaluation board is equipped with the Raspberry Pi connector, which allows for quick and easy setup. Additionally the kit is delivered with a board and speaker stand allowing users to quickly evaluate the performance of the solution.
“Amazon’s goal is for developers and device makers to have access to a wide range of reference solutions that fit their needs,” said Priya Abani, Director, Alexa Voice Service. “We’re excited to be working with Microsemi to provide device manufacturers with a way to quickly and easily integrate Alexa into their products across a variety of form factors, including wall-mounted and on-table devices, smart speakers, and connected home products.”
While the Raspberry Pi runs the Amazon AVS client and Alexa wake word detection, the Timberwolf solution runs all front-end audio processing enabling significantly improved speech recognition accuracy. The signal processing technology implemented by the Timberwolf audio processor includes:
-Noise reduction
-Beam forming
-Barge-in support
-CLE mic pickup
-Full duplex two-way audio
-Stereo acoustic echo cancellation
-Direct mic interface as well as Serial Peripheral Interface (SPI) and Inter-IC Sound (I2S)/time-division multiplexing (TDM) connection to the Raspberry Pi
Availability
The Microsemi AcuEdge Development Kit for Amazon AVS is generally available through distributors Arrow and Future Electronics. It retails for $299.
About the AcuEdge Technology and Timberwolf ZL38063 Multi-Mic Audio Processor
Microsemi’s AcuEdge's technology consists of license-free, royalty-free audio intellectual property (IP) solutions. It is the compilation of various IPs targeted at processing voice signals in conjunction with noise reduction algorithms, automatic gain control, echo cancellation, psychoacoustic noise reduction, howling detection and rejection. These powerful capabilities are the foundation for enterprise level automatic speech recognition, sound classification and other intelligent decision-making functions based on sound and audio detection. The ZL38063 Timberwolf provides a powerful digital signal processor (DSP) with voice specific hardware accelerators, three digital microphone interfaces, two independent 16-bit digital-to-analog converters (DACs) with headphone drivers and two flexible time-division multiplexed (TDM) interfaces in a single 64-pin QFN package. Additional features include 44.1/48 kHz stereo music playback with voice, ultralow and standby off power, and stationary and psychoacoustic noise reduction. It can run unattended (controllerless) and offers self-booting into a configured operational state. In addition, the ZL38063 has built-in support for G.712 and G.722 and is G.168 and G.169 compliant line echo cancellation (LEC). To learn more about the ZL38063 visit https://www.microsemi.com/products/audio-processing/home-automation/zl38063. For more information about the Development Kit for Amazon AVS visit https://www.microsemi.com/amazon-alexa-kit.
