System and method for updating biometric evaluation systems

1. A method for adjusting the threshold in a biometric comparison system, the method comprising:

over a series of biometric comparisons of authentication voice prints to enrollment voice prints, storing the authentication voice prints, and storing a plurality of scores resulting from the biometric comparisons in a first set of a plurality of scores;

creating a second set of biometric comparisons each based on a pairing of a stored authentication voice print and an enrollment voice print, each biometric comparison resulting in a score, the plurality of resulting scores forming a second set of a plurality of scores;

wherein the pairing of the stored authentication voice print and the enrollment voice print is a random pairing;

merging the first set of a plurality of scores with the second set of a plurality of scores to produce a third set of a plurality of scores, the third set of a plurality of scores comprising a plurality of discrete values, each discrete value taken from one of the first set of scores and the second set of scores; and

performing an iterative process over the third set of scores to update the parameters of the Gaussian distribution of the third set of scores.

2. The method of claim 1 , wherein the series of biometric comparisons occurs during authentication processes.

3. The method of claim 1 , wherein each of the stored voice prints used for the biometric comparisons results in a score being stored, resulting from the biometric comparisons, in a first set of scores.

4. The method of claim 1 , comprising creating an authentication threshold based on the updated parameters of the Gaussian distribution of the third set of scores.

5. The method of claim 1 , wherein the parameters of the Gaussian distribution comprise a weight, mean and variance.

6. The method of claim 1 , wherein the iterative process comprises an expectation-maximization algorithm.

7. The method of claim 1 , comprising performing an authentication using a threshold based on the updated parameters of the Gaussian distribution.

8. The method of claim 1 , comprising displaying the Gaussian distribution of the third set of scores.

9. The method of claim 1 , wherein creating a second set of biometric comparisons is executed in background during the series of biometric comparisons of authentication voice prints to enrollment voice prints.

10. A system for adjusting the threshold in a biometric comparison system, the system comprising:

a memory, and

a processor configured to:

over a series of biometric comparisons of authentication voice prints to enrollment voice prints, store the authentication voice prints, and store a plurality of scores resulting from the biometric comparisons in a first set of a plurality of scores;

create a second set of biometric comparisons each based on a pairing of a stored authentication voice print and an enrollment voice print, each biometric comparison resulting in a score, the plurality of resulting scores forming a second set of a plurality of scores;

wherein the pairing of the stored authentication voice print and the enrollment voice print is a random pairing;

merge the first set of a plurality of scores with the second set of a plurality of scores to produce a third set of a plurality of scores, the third set of a plurality of scores comprising a plurality of discrete values, each discrete value taken from one of the first set of scores and the second set of scores; and

perform an iterative process over the third set of scores to update the parameters of the Gaussian distribution of the third set of scores.

11. The system of claim 10 , herein the series of biometric comparisons occurs during authentication processes.

12. The system of claim 10 , wherein each of the stored voice prints used for the biometric comparisons results in a score being stored, resulting from the biometric comparisons, in a first set of scores.

13. The system of claim 10 , wherein the processor is configured to create an authentication threshold based on the updated parameters of the Gaussian distribution of the third set of scores.

14. The system of claim 10 , wherein the parameters of the Gaussian distribution comprise a weight, mean and variance.

15. The system of claim 10 , wherein the iterative process comprises an expectation-maximization algorithm.

16. The system of claim 10 , wherein the processor is configured to perform an authentication using a threshold based on the updated parameters of the Gaussian distribution.

17. A method for adjusting the threshold in a biometric voiceprint comparison system, the method comprising:

collecting the results of comparisons of authentication voice prints to enrollment voice prints, and collecting the authentication voice prints;

collecting a plurality of results of a set of biometric comparisons each of the plurality of results based on a pairing of an authentication voice print and an enrollment voice print;

merging a plurality of results of comparisons of authentication voice prints to enrollment voice prints and a plurality of results of a set of biometric comparisons each based on a pairing of an authentication voice print and an enrollment voice print to produce a set of results, wherein the pairing of the stored authentication voice print and the enrollment voice print is a random pairing, the produced set of results comprising a plurality of discrete values, each discrete value taken from one of: the plurality of results of comparisons of authentication voice prints to enrollment voice prints; and the plurality of results of a set of biometric comparisons; and

performing an iterative process over the set of results to update the parameters of the Gaussian distribution of the third set of scores.

18. The method of claim 9 , comprising displaying the Gaussian distribution of the set of results.