Authentication via a dynamic passphrase

1. A computer-implemented method for voice authentication of a customer in a self-service system, the computer implemented method comprising:

creating a plurality of passphrases from recorded parts of prior interactions of the customer with an agent, the interactions comprising phrases the user has uttered, the phrases having enough words to create a phrase having a sufficient ability to be voice recognized by a voice biometric model;

receiving a request for authentication of the customer, the customer being enrolled in the self-service system with a text-independent voice print without requesting the user utter a particular phrase;

determining a passphrase from the plurality of passphrases to transmit to the customer based on comparing each of the plurality of passphrases to a text-dependent or text-independent voice biometric model, and wherein the determining of the passphrase comprises randomly selecting the passphrase from one or more of the plurality of passphrases;

transmitting a request to the customer to repeat the passphrase;

receiving an audio stream of the passphrase;

authenticating the customer by comparing the audio stream of the passphrase against the text-independent voice print; and

if the customer is authenticated, then storing the audio stream of the passphrase;

wherein the plurality of passphrases is updated when more than a predefined percentage of customers of a system that executed the method are enrolled with the same passphrases, the updating based on computerized text.

2. The computer-implemented method of claim 1 comprising upon receipt of a subsequent request for authentication of the customer, determining another passphrase that is different from the previous passphrase.

3. The computer-implemented method of claim 1 further comprising:

for each subsequent request for authentication, presenting the customer with a unique passphrase of the plurality of passphrases; and

storing an audio stream of each corresponding unique passphrase as recited by the customer.

4. The computer-implemented method of claim 1 wherein determining the passphrase further comprises selecting the passphrase from the plurality of passphrases such that the same passphrase is not used more than a minimum number of reuse times.

5. The computer-implemented method of claim 1 wherein determining the passphrase further comprising combining two or more passphrases from the plurality of passphrases.

6. The computer-implemented method of claim 1 further comprising for each passphrase in a group of passphrases that is transmitted to the customer a maximum number of use times, deleting the corresponding passphrases from the plurality of passphrases.

7. The computer-implemented method of claim 1 wherein the plurality of passphrases is input by a user.

8. The computer-implemented method of claim 1 wherein the plurality of passphrases is automatically populated.

9. The computer-implemented method of claim 1 wherein the determining of a passphrase from the plurality of passphrases is based on a highest likelihood of authenticating the customer.

10. The computer-implemented method of claim 9 , comprising:

if multiple passphrases from the plurality of passphrases have the highest likelihood of authenticating the customer, then determining the multiple passphrases as the passphrase to transmit to the customer.

11. A system for voice authentication of a customer comprising:

a memory; and

a processor configured to:

create a plurality of passphrases from recorded parts of prior interactions of the customer with an agent, the interactions comprising phrases the user has uttered, the phrases having enough words to create a phrase having a sufficient ability to be voice recognized by a voice biometric model;

receive a request for authentication of the customer, the customer being enrolled in the self-service system with a text-independent voice print without requesting the user utter a particular phrase;

determine a passphrase from the plurality of passphrases to transmit to the customer based on comparing each of the plurality of passphrases to a text-dependent or text-independent voice biometric model, and wherein the determining of the passphrase comprises randomly selecting the passphrase from one or more of the plurality of passphrases;

transmit a request to the customer to repeat the passphrase;

receive an audio stream of the passphrase;

authenticate the customer by comparing the audio stream of the passphrase against the text-independent voice print; and

if the customer is authenticated, then store the audio stream of the passphrase;

wherein the plurality of passphrases is updated when more than a predefined percentage of customers of a system that executed the method are enrolled with the same passphrases, the updating based on computerized text.

12. The system of claim 11 wherein the processor is configured to upon receipt of a subsequent request for authentication of the customer, determine another passphrase that is different from the previous passphrase.

13. The system of claim 11 wherein the processor is configured to:

for each subsequent request for authentication, present the customer with a unique passphrase of the plurality of passphrases; and

store an audio stream of each corresponding unique passphrase as recited by the customer.

14. The system of claim 11 wherein determining the passphrase comprises selecting the passphrase from the plurality of passphrases such that the same passphrase is not used more than a minimum number of reuse times.

15. The system of claim 11 wherein determining the passphrase comprises combining two or more passphrases from the plurality of passphrases.

16. The system of claim 11 wherein the processor is configured to for each passphrase in a group of passphrases that is transmitted to the customer a maximum number of use times, delete the corresponding passphrases from the plurality of passphrases.

17. The system of claim 11 wherein the plurality of passphrases is automatically populated.