CEVA, Inc., the licensor of wireless connectivity and smart sensing technologies and co-creation solutions, has announced that its audio front end (AFE) software solution has become Alexa Voice Service (AVS) qualified.
The solution, which combines CEVA’s ClearVox far-field noise reduction and voice processing software together with WhisPro, voice user interface neural network based keyword spotting (KWS) software, is a robust, ultra-low power software package ready for integration with AVS-enabled devices such as smart speakers, soundbars and more.
AVS is Amazon’s cloud-based service that allows device makers to integrate an ever-increasing set of Alexa features and functions into compatible devices. By garnering an AVS qualification for its audio front end software solution, CEVA’s semiconductor, ODM and OEM customers can utilize this software solution to seamlessly add Alexa-enabled services to their target device.
For companies looking to develop a complete smart and connected SoC that brings the power of Alexa to its customers, CEVA offers a broad range of licensable IP for audio System-on-Chips (SoCs), including audio/voice DSPs and AI engines, sensor fusion software, and wireless connectivity solutions for Bluetooth, Wi-Fi, UWB, and cellular IoT. This enables customers to accelerate their complete SoC development and bring the power of Alexa to their target end devices.
Chad Lucien, VP & GM Sensors and Audio BU at CEVA, commented: “Becoming AVS qualified is powerful for any audio front end software solution and we are proud to have achieved this milestone for our ClearVox far-field and WhisPro software. AVS unlocks an incredible amount of functionality and experiences for smart devices, and we look forward to seeing how our software brings Alexa to a new generation of consumer, industrial and IoT devices.”
Developed in-house and leveraging CEVA’s vast expertise in audio and voice processing, CEVA’s AVS qualified ClearVox and WhisPro audio front-end software packages incorporate advanced algorithms that cope with different acoustic scenarios and microphone configurations, including optimised software for speaker direction of arrival, multi-mic beamforming, noise suppression and acoustic echo cancellation, as well as the related firmware and driver software.
WhisPro is an AVS qualified neural network-based keyword spotting (KWS) software package, allowing customers to add wake-words and commands to voice-enabled IoT devices. As a voice user interface, WhisPro is targeting the rapidly growing use of voice as a primary human interface for intelligent cloud-based services and edge devices. WhisPro provides a customizable (any language, any keyword) wake-word and keyword voice interface.
This allows users of smart TVs, smart speakers, soundbars, and other voice-enabled IoT devices to interact with cloud-based voice assistant services, as well as enabling voice activation on edge devices through its small footprint and processing needs, without cloud connectivity.