We provide multimodal digital identity verification through facial and voice biometrics. A security test that can add more accuracy to fraud detection is voice (speaker) verification.
The PresentID speaker verification API/SDK checks whether two voices belong to the same person or not. This capability is potentially useful in call centers.
We have proposed a deep learning-based method for speaker verification. Our team has worked on this project for over a year and the accuracy exceeded criteria such as the accuracy of the Andrew Zisserman group paper from the university of oxford. Unlike other text-dependent methods, our system is text- and language-independent.
Our model's processing speed is less than 1 sec. The system identifies a person by simply checking two voices lasting 4 seconds. Our system works perfectly in English, French, Spanish, German, Persian and Arabic, even in a noisy environment.
First, read PresentID's privacy notice carefully before trying the demo.
1. Open this page on your mobile phone
2. Tap the record icon
3. Allow access to your recorder
4. Tap the record icon to stop the recorder
5. Press the play button and listen to your voice
6. If confirmed, tap download
7. Repeat the above for the second voice
8. Finally, tap compare
The PresentID speaker verification API checks whether two voices belong to the same person or not. This capability is potentially useful in call centers.Free try
67, Rue Jean Jaures, 94800 Villejuif, France
5, parvis Alan-Turing, 75013 Paris, France
+33 6 46 46 75 15