“…Sensory says the system now allows users to be enrolled passively, with the system’s AI dynamically modelling their voice biometrics as they speak – a functionality that may tie into the company’s assertion that the system works with all languages and dialects.”
Sensory has upgraded the voice biometrics capabilities of its TrulySecure platform. The enhancements arrive after an upgrade to the platform’s facial recognition capabilities earlier this year.
Version 2.0 of the TrulySecure Speaker Verification (TSSV) SDK boasts of improvements in a number of areas. Equal error rates are down by 25 percent compared to version 1.0 of the solution, and it now offers a liveness challenge feature requiring specific input from a user. Users no longer need to say specific passphrases in order for their voices to be tracked, and perhaps more remarkably, Sensory says the system now allows users to be enrolled passively, with the system’s AI dynamically modelling their voice biometrics as they speak – a functionality that may tie into the company’s assertion that the system works with all languages and dialects.
In a statement announcing the improvements, Sensory CEO Todd Mozer asserted that the company’s TrulySecure face and voice biometrics solutions have already proven to be “a huge market success” thanks to integrations with companies like LG, Motorola, and Samsung. “We believe TrulySecure Speaker Verification 2.0 has a lot of market potential, especially with the addition of new security features, text independence, anti-spoof approaches and much more,” he added.
The upgraded SDK is available to device and app developers looking to integrate voice interaction into their solutions, with the package priced at $2,500 and including five hours of technical support. It’s an offer that could indeed prove highly appealing as voice interfaces become more and more popular across a range of consumer devices.
Follow Us