Authentication via a dynamic passphrase

Patent metadata

Field	Value
Publication number	US-11625467-B2
Application number	US-202117329425-A
Country	US
Kind code	B2
Filing date	May 25, 2021
Priority date	Aug 9, 2017
Publication date	Apr 11, 2023
Grant date	Apr 11, 2023

Abstract

A computerized method for voice authentication of a customer in a self-service system is provided. A request for authentication of the customer is received and the customer is enrolled in the self-service system with a text-independent voice print. A passphrase from a plurality of passphrases to transmit to the customer is determined based on comparing each of the plurality of passphrases to a text-dependent or text-independent voice biometric model. The passphrase is transmitted to the customer, and when the customer responds, an audio stream of the passphrase is received. The customer is authenticated by comparing the audio stream of the passphrase against the text-independent voice print. If the customer is authenticated, then the audio stream of the passphrase and the topic of the passphrase may be stored.

First claim

What is claimed is:

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 is enrolled in the self-service system with a text-independent voice print;
determining a passphrase from a 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;
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;
if the customer is authenticated, then storing the audio stream of the passphrase; and

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.

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 wherein the plurality of passphrases is input by a user.

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

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

9. The computer-implemented method of claim 1 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.

10. The computer-implemented method of claim 9 wherein updating the plurality of passphrases is based on computerized text.

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 is enrolled in the self-service system with a text-independent voice print;
determine a passphrase from a 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;
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;
if the customer is authenticated, then store the audio stream of the passphrase; and

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.

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 plurality of passphrases is automatically populated.

17. The system of claim 11 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.

18. The system of claim 11 wherein the processor is configured to update the plurality of passphrases based on computerized text.

Assignees

• Nice Ltd

Inventors

• Keret Matan
• Buzaglo Amnon

Classifications

• G10L17/14

  Use of phonemic categorisation or speech recognition prior to speaker recognition or verification · CPC title

• G06F2221/2103

  Challenge-response · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title

• G10L17/24

  the user being prompted to utter a password or a predefined phrase · CPC title

• H04L63/0861

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title