THE TRIGGER TECHNOLOGIST
Other speech technology industry leaders said that delivering low-power speech trigger technology capable of running on Bluetooth devices, mobile phones, wearables, and other consumer electronics was impossible, but Todd Mozer would have none of it. As chairman and CEO of Sensory, Mozer has been determined to make truly hands-free speech technology both functional and enjoyable to use, and has succeeded with his company’s TrulyHandsfree voice trigger, TrulyNatural speech recognition, and TrulySecure speaker verification product lines.
The company’s flagship TrulyHandsfree voice recognition, voice trigger, speaker identification, speaker verification, and command-and-control technology is already deployed in more than 1 billion products from such notable manufacturers as AT&T, Samsung, Sony, Toshiba, Kenwood, Hasbro, Mitsubishi, and more. And this year alone, Mozer inked key alliances that are bringing TrulyHandsfree to Vuzix M300 smart glasses, Samsung’s Galaxy S7 and Galaxy S7 Edge smartphones, Intel’s latest software-on-a-chip platforms, and Philips’s BeClear Speech Enhancement platform.
The latest version, introduced just about a year ago, features deep learning that, according to Sensory’s internal testing, offers improved performance and a 60 percent to 80 percent decrease in word error rates. TrulyHandsfree 4.0 offers new phrase-spotting techniques and a neural networking engine that supports deep learning acoustic models, dramatically improving speech recognition accuracy in real-world noise. Sensory uses a unique form of neural network with deep learning to achieve acoustic models that are much smaller than other offerings.
Even more companies and developers will be able to benefit from that technology following the company’s June launch of the TrulyHandsfree SDK, allowing speech triggers and commands to be built into apps with fewer than 20 lines of code.
Sensory’s latest version of TrulySecure—version 2.0, released in November—coincided with the launch of a TrulySecure partner program, providing discounts and other benefits to app developers interested in trying, testing, or deploying apps featuring TrulySecure 2.0 biometric authentication.
“What really impresses me about Todd is his long commitment to speech technology, and specifically, his focus on embedded and small-footprint speech recognition,” says Deborah Dahl, principal at Conversational Technologies and chair of the World Wide Web Consortium’s Multimodal Interactions Working Group. “He focuses on what he does best and excels at that.”