The 2016 Speech Industry Star Performers: Sensory

Sensory Contributes to the IoT with Embedded Technology

Sensory has embedded its speech recognition into roughly a billion products from hundreds of consumer electronics manufacturers, but the company isn’t stopping there. Thanks to a few key partnerships this year, it’s taking its technology even farther.

Through a recent partnership with Vuzix, Sensory will embed its TrulyHandsfree voice recognition, voice trigger, speaker identification, speaker verification, and command-and-control technologies on the Vuzix M300 smart glasses to improve the efficiency of workflows in warehouses, field service operations, telemedicine, and many other use cases.

Other recent moves include incorporating the Sensory TrulyHandsfree technology into Samsung’s latest Samsung Galaxy S7 and Galaxy S7 Edge smartphones. In March, the company also began embedding its TrulyHandsfree technology on many of Intel’s latest software-on-a-chip (SoC) platforms. In November 2015, Sensory packaged its TrulyHandsfree and TrulyNatural speech recognition technologies with Philips’s BeClear Speech Enhancement algorithms to improve accuracy in noisy environments.

“We tested various implementations of our BeClear Speech Enhancement algorithms with Sensory’s industry-­leading speech recognition engine and have seen impressive improvements in accuracy in noiseless to high-noise environments,” said Navin Natoewal, general manager of media interaction at Philips, in a statement. He added that Philips is “working with Sensory to offer a packaged solution…that will ensure that devices hear their users, even at far distances in the noisiest environments.”

Even more companies and developers will be able to benefit from Sensory’s TrulyHandsfree technology following the company’s June launch of the TrulyHandsfree SDK, the next evolution of its embedded small-footprint voice user interface platform.

Sensory in January also released TrulyHandsfree on the Samsung ARTIK developer platform, enabling ARTIK users to design Internet of Things products that offer a completely hands-free user experience.

But Sensory isn’t just enabling developers to do more with its products. The company is doing plenty of innovation on its own, as evidenced by its May release of a free and highly secure face and voice biometric fusion app called AppLockFace/Voice Recognition. The app, powered by TrulySecure, combines advanced deep learning face and voice biometric authentication technologies.

Its latest version of TrulySecure, version 2.0—which was released in November—coincided with the launch of a TrulySecure partner program that provided discounts and other benefits to app developers interested in trying, testing, or deploying apps featuring TrulySecure 2.0 biometric authentication.

“We recently assessed Sensory’s TrulySecure 2.0 technology…and were left very impressed,” said Darrell Geusz, founder of the ID Trust Network, in a statement. “Sensory’s implementation of multiple techniques for combining different biometric modalities delivers high accuracy and novel user flexibility.”

“Sensory reaps the benefits of its long history of innovation in device-based biometrics and speech technologies. TrulySecure 2.0 continues to leverage early deployment of neural net technology for high accuracy in mobile phones and embedded devices,” notes Dan Miller, founder and lead analyst at Opus Research.

“Sensory is clearly the leader in providing low-power, always-listening technology, and recent additions to their technology also support more local command and control without requiring speech data to be sent over the Internet,” adds Bill Meisel, president of TMA Associates. “A wake-up word that is local and doesn’t transmit speech over the internet until awoken is key to the growth of the much-hyped Internet of Things and voice-controlled home devices in general.”

Deborah Dahl, principal at Conversational Technologies and chair of the World Wide Web Consortium’s Multimodal Interactions Working Group, agrees. “Sensory has always been in the forefront of embedded speech recognition, with its TrulyHandsfree product, a fast, accurate, and small-footprint speech recognition system. Its newer product, TrulyNatural, is groundbreaking because it supports large vocabulary speech recognition and natural language understanding on embedded devices, removing the dependence on the cloud,” she says. “While cloud-based recognition is the right solution for many applications, if the application must work regardless of connectivity, embedded technology is required. The availability of TrulyNatural embedded natural language understanding should make many new types of applications possible.”