We provide multi-faceted digital identity verification through facial and voice biometrics. One security test that can add more accuracy to fraud detection is voice verification.

GATA’s Voice Comparison API/SDK checks whether two voices belong to the same person. This capability is potentially useful in call centers.

We have proposed a deep learning-based method for voice comparison. Our team has been working on this project for over a year, and its accuracy has surpassed benchmarks such as the accuracy of the paper by Andrew Ziserman’s group at the University of Oxford. Unlike other text-based methods, our system is text- and language-independent.

Our model processing speed is less than 1 second. The system identifies a person by simply examining two 4-second voices. Our system works perfectly in English, French, Spanish, German, Persian, and Arabic, even in noisy environments.