ID R&D says IDVoice now industry’s fastest and most accurate speech-independent verification solution
ID R&D has launched the newest version of its voice biometric security solution, IDVoice, which the company says is now the fastest and most accurate text-independent biometric verification tool in the industry.
The new version of IDVoice drastically reduces the required length of audio samples, with increased authentication accuracy. Compared to the typical industry standard requirement of seven to ten seconds of free speech to perform a positive voice identification, with varying levels of accuracy, IDVoice now requires only one to two seconds of speech for high accuracy, according to the announcement. In testing, ID R&D found IDVoice has an Equal Error Rate (EER) of 0.3 percent on microphone collected data and 0.6 percent with a telephone.
“ID R&D is excited to deliver this next-generation approach to voice biometrics which merges robust security and functional usability into a single solution,” said Konstantin Simonchik, Co-Founder and Chief Science Officer of ID R&D. “Through groundbreaking algorithms comprised of x-vectors and Convolutional Neural Networks, IDVoice offers the most accurate, fastest, and easiest solution for all industries looking to enhance security and UX through voice biometrics. This product is the next step in our journey to provide AI-based multimodal biometrics solutions that deliver unmatched security through a wholly frictionless experience for the end user.”
The company updated IDVoice a month ago, and also announced that IDVoice and its IDBehave behavioral biometric product have been added to Samsung’s SDS Digital Identity Platform. It also joined the Google Cloud Startup Program to accelerate the development and training of its biometric software.