ArkX Integrates Sensory’s Voice Tech Into Far-field Voice Platform

ArkX Labs is teaming up with Sensory to increase the appeal of its own EveryWord voice solutions. EveryWord specifically offers far-field voice capabilities, which means that it can pick up voice commands at a greater distance (and when there is more interference) than other voice capture products.

The partnership with Sensory will further improve the voice recognition capabilities of the platform. ArkX will be integrating a number of Sensory technologies into EveryWord, thereby increasing the number of features that are available to its clients. Sensory’s portfolio includes more general speech recognition and natural language understanding tech, in addition to more specialized utilities like voice biometrics and extensive wake word and sound identification libraries. The arrangement also covers Sensory’s facial recognition tech.

EveryWord itself is geared toward equipment manufacturers that want to add voice recognition to their smart devices. The platform can help manufacturers bring voice products to market more quickly. Sensory’s tech will enable the creation of custom wake words, and allow EveryWord to offer support for two dozen unique languages and dialects. ArkX is pitching its enhanced solution to manufacturers in multiple sectors, and argues that its solution is ideal for everything from consumer appliances and wearables to automotive voice assistants.

“Voice adoption continues to grow rapidly, and brands are always exploring ways to streamline the process of integrating a convenient voice UX into their products,” said Sensory CEO Todd Mozer. “Working with ArkX Labs provides the industry a turn-key solution for integrating advanced speech recognition capabilities into their products that can enable OEM-brand-specific wake words and other attractive advanced feature sets.”

According to ArkX, EveryWord has triple the range of other voice capture solutions, and can pick up commands around corners or in noisy environments. The solution will also suppress sound from a single point like a TV. EveryWord consists of a Voice Processing Module, an Integrated Voice Module, and an AVS Development Kit with Amazon Voice Services approval.

Sensory, meanwhile, recently released a beta version of a new SensoryCloud AI-as-a-Service processing platform. Before that, the company launched a speech recognition module that has been optimized for children.

–

January 26, 2022 – by Eric Weiss