A True User Imposter TestA True User Imposter Test evaluates the False Accept and False Accept rates of a Voice Biometric system by using existing users of the system to simulate imposter attempts. This is an essential step in establishing the appropriate Biometric threshold. is part of the TuningTuning, in the context of voice biometrics, refers to the process of adjusting the configuration and parameters of a voice biometric system to optimize its performance for a particular task or environment. and Calibration process for Voice BiometricsVoice Biometrics uses the unique properties of a speakers voice to confirm their identity (authentication) or identify them from a group of known speakers (identification). systems. It uses real user data to simulate imposter access attempts. For example:
- 1000 speakers with 1 enrollment utterance and 4 verification utterances provide:
- 4,995,000 imposter access attempts (1000 speakers x 999 imposters x 5 utterances ) imposter attempts and
- 4000 genuine access attempts (1000 speakers x 4 utterances).
As each trial generates a biometric score, they can be graphically plotted to help understand the performance of the system.
Based on the results of the True User Imposter Test, it is possible to calibrate the biometric decision threshold such that the risk of a False AcceptA False Accept is when an imposter is incorrectly accepted as the genuine user during authentication. (FAA False Accept is when an imposter is incorrectly accepted as the genuine user during authentication.) is consistent with the implementing organisation’s risk appetite.