New version of ID R&D voice biometric solution boasts cross-channel enrollment and 10x speed boost

ID R&D has released a new version of its voice biometric software which provides simplified enterprise integration and cross-channel enrollment, according to a company announcement.

IDVoice v2.7 combines the latest advances in artificial intelligence and voice technology to increase biometric matching speed by tenfold over it previous algorithm, and improve the enrollment and authentication process across multiple channels, the company says. The company says its previous x-Vector algorithm was already faster and more accurate with a smaller footprint than i-Vector solutions, as ID R&D Chief Science Officer Konstantin Simonchik told Biometric Update in an interview in late-2018. Along with essential functionality for a robust, effective, and efficient omnichannel enterprise voice biometric strategy, IDVoice v2.7 allows a single customer enrollment to be used across all channels. Previously, the need for customers to enroll separately for each interface has discouraged adoption across multiple interfaces for customer authentication.

Developers set a parameter in the API to inform ID R&D’s biometric engine of the source of a voice sample, and the engine automatically recalibrates the probability scoring if the enrollment source and the verification source do not match. This is possible, according to the announcement, because ID R&D designed its biometric engine architecture to be independent of channel, language, and age variance, and to be resilient to environmental noise.

“As enterprises migrate to conversational interfaces through mobile, web, and call center applications, a strong cross-channel voice authentication capability is essential,” says Simonchik. “With IDVoice v2.7, we are making it much easier and more efficient for enterprises to deploy voice biometrics consistently on all channels using the programming tools they prefer.”

IDVoice v2.7 also features an improved Signal to Noise calculator, an improved Voice Activity Detector, and wrappers in Python and Java, enabling faster integration by many developers. ID R&D also ships the solution as a Docker image to facilitate flexible cloud deployments.

“Even though the use of digital and mobile channels are on the rise, we’re witnessing explosive demand of voice biometrics as enterprises address the need to provide a user interface that mixes security and convenience when customers contact agents over the voice channel,” comments Dan Miller, founder and lead analyst, Opus Research. “ID R&D’s cross-channel authentication capability delivers the kind of zero-effort authentication that’s fast becoming a necessity for businesses with customers who reach out across multiple devices and channels.”

Several major biometrics integrators and financial institutions around the world are currently testing and deploying IDVoice v2.7.

ID R&D raised $5.7 million to accelerate the marketing and international sales of its biometric technologies.

Article Topics

artificial intelligence  |  authentication  |  biometric matching  |  biometrics  |  enterprise  |  ID R&D  |  voice