ID R&D Delivers Voice Biometrics Authentication Accuracy Requiring Just 1-2 Seconds of Free Speech with IDVoice
ID R&D, a biometric solutions provider offering proprietary AI-based behavioral, voice, and anti-spoofing user authentication capabilities, released the newest version of its voice biometric security solution, IDVoice. The product’s enhancements allow ID R&D to deliver the industry’s fastest and most accurate text-independent biometric verification.
IDVoice is an AI-based, mobile-optimized, low-footprint voice biometric solution that instantly authenticates users by evaluating individual users’ biometric voice signature, comprised of over 100 distinctive characteristics. This newest version requires drastically shorter audio samples for text-independent voice biometric verification, while increasing authentication accuracy. Until now, industry standards required a minimum of seven to ten seconds of free speech for a positive voice ID with varying levels of accuracy. IDVoice saysit returns an Equal Error Rate (EER) of just 0.3% on microphone collected dataset (test was based on the publicly-available CSTR VCTK Corpus) and 0.6% in telephone channels (NIST SRE 2010 telephone Core test).R VCTK Corpus data set.
ID R&D’s IDVoice is part of the company’s product suite which includes:
- IDSquared, the company’s solution for mobile login which combines facial recognition and behavioral biometrics
- IDBehave, its behavioral biometrics solution
- IDAnti-Spoof, its security solution that can distinguish between human voice and computer-generated or modified voice (TTS and VC)
- SafeChat, a continuous multimodal biometric verification product for chatbots and virtual assistants
The latest version of IDVoice is available now to ID R&D customers.