Auraya Releases ArmorVox2015
Auraya Systems this week released ArmorVox2015, a voice biometric solution complete with the Universal Speaker Recognition Engine that fuses text-dependent and text-independent technology and active and pssive biometrics into a single software license.
New to ArmorVox2015 is an extended front-end that improved accuracy, new noise cancellation technology, and new acoustic filtering that extends the accuracy further; especially for cross-channel solutions where speakers enroll in one channel and verify in another.
ArmorVox2015 also offers new tuners that are embedded in the product to optimize the models to the accent, language, and communications environment of the population of enrolled users. The upshot of all these new capabilities is a two- to four-fold improvement in voice biometric accuracy and robustness.
This new capability allows end-users such as banks, governments and financial services, to utilise their large stock of voice logs captured from previous customer calls to bootstrap their voice biometric deployment. These recording can be exported from their voice logging systems to ArmorVox2015 to create a ready-made voiceprint database from which to authenticate customers without need for explicit enrollment. And even if the voice logs are mono (that is both customer and call centre agent in the same channel), Auraya speaker splitting technology can separate the speakers and create voiceprints for both sides of the conversation.