Since the explosive interest in connected devices, manufacturers have looked for ways to liberate product designs with portable and battery-powered capabilities. Now, they’re also interested in bringing voice interaction to these products, while maintaining cost-effectiveness and performance. It’s a tall order to fill, which is why we’re excited to add the DSP Group HDClear 3-Mic Development Kit for Amazon AVS to our portfolio of qualified developer solutions. The audio front end solution enables low-power wake-on-voice operation and far-field voice recognition performance with only three microphones.
DSP Group’s development kit includes the audio-centric DBMD5 processor configured to enable wake-on-voice functionality while conserving battery life and extending usability in power-sensitive applications. The self-contained audio processing solution incorporates HDClear voice enhancement signal processing algorithms, first-stage wake word engine, and low-power Voice Activity Detector with the DSP chip. The system supports three power operating modes: low-power 1-mic voice trigger mode, 3-mic noise reduction mode with beamforming and noise reduction, and 3-mic barge-in mode with Acoustic Echo Cancellation (AEC) processing. This optimized architecture makes it possible for battery-powered devices to continuously monitor voice activity and detect the “Alexa” wake word while minimizing system-level power consumption.
Target applications for DSP Group’s solution include battery-powered devices, especially those that are powered part time by electrical mains. Portable smart speakers, IoT gadgets, and smart home devices align to the features of this reference solution. However, the solution is not limited to that device category. DSP Group’s solution in full-power mode meets the Alexa Voice Service far-field requirements with only three microphones, making it suitable for a broad range of applications. Additionally, DSP Group has an established footprint in gateway, hub, and telephony devices, and expects existing customers in those segments to adopt this solution.
“We envision a future where customers interact with Alexa everywhere and from any device,” said Priya Abani, Director, Alexa Voice Service. “We’re excited to work with DSP Group to achieve this vision and offer developers additional tools that add to the various resources they already have available to build Alexa-enabled devices.”
The development kit is comprised of the HDClear DSP Board with dual-core DBMD5 processor, a 3-microphone triangular array with 360-degree pick up, a Raspberry Pi 3 with SD card and power supply, and mic array-to-DSP board cables. HDClear algorithms enable beamforming, noise reduction, and Acoustic Echo Cancellation capabilities. The reference client application for Raspberry Pi is built using the AVS Device SDK.
How to Integrate Alexa into Your Product
AVS enables developers to integrate Alexa directly into their products, bringing the convenience of voice control to any connected device. Developers can quickly get an Alexa-enabled prototype up and running by following our hands-on tutorials. Get an overview of AVS and start building with the AVS Device SDK now.
What Is AVS?
AVS is a customizable suite of development tools and resources that make it easy to integrate Alexa directly into your products and bring voice-forward experiences to customers. Through AVS, you can add a new natural interface to your products and offer customers access to a growing number of Alexa features, smart home integrations, and skills. Visit the AVS Developer Portal to get started.
Source: Alexa Developer Blog