Leveraging multiple audio channels for authentication

• US 10,665,244 B1
• Filed: 01/04/2019
• Issued: 05/26/2020
• Est. Priority Date: 03/22/2018
• Status: Active Grant

• Current Assignee: Pindrop Security, Inc.
• Original Assignee: Pindrop Security, Inc.
• Inventors: Gupta, Payas, Nelms, II, Terry
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US16/240,602
• Time in Patent Office: 508 Days
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: H04L 63/0853 using an additional device, e.g. smartcard, SIM or a different communication terminal cryptographic mechanisms or cryptographic arrangements for entity authentication involving additional secure or trusted devices H04L9/3234
• CPC Class Codes: H04M 2203/6054 Biometric subscriber identification
• CPC Class Codes: H04M 2203/6081 Service authorization mechanisms
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04W 12/06 Authentication
• CPC Class Codes: H04W 12/63 Location-dependent; Proximity-dependent
• CPC Class Codes: H04W 12/65 Environment-dependent, e.g. using captured environmental data

Abstract

Disclosed herein are embodiments of systems, methods, and products comprises an authentication server for authentication leveraging multiple audio channels. The server receives an authentication request regarding a user upon the user interacting with a first electronic device. The server requests the first device to transmit a first audio file of an audio sample to the server. The audio sample may be the user'"'"'s audio command or a machine-generated audio signal. The server requests a second electronic device to transmit a second audio file that is the recording of the same audio sample to the server. The second electronic device is a trusted device in proximity of the first device and executes an authentication function to enable the recording and transmitting of the audio sample. The server determines a similarity score between the first audio file and the second audio file and authenticates the user based on the similarity score.

Claims

1. A computer implemented method comprising:

receiving, by a server and from a first electronic device, a first audio file of a user'"'"'s voice captured by the first electronic device in response to receiving a voice command from the user;

transmitting, by the server to a second electronic device, a command to trigger the second electronic device to capture the user'"'"'s voice in response to the first electronic device receiving the voice command;

receiving, by the server and from the second electronic device, a second audio file of the user'"'"'s voice captured by the second electronic device in proximity to the first electronic device in response to the second electronic device receiving the command;

comparing, by the server, the first and second audio files to generate a similarity score that determines a likelihood that the first electronic device and the second electronic device captured the user'"'"'s voice at the same time; and

authenticating the user, by the server, in response to the server determining that the similarity score is above a threshold.

2. The method of claim 1, wherein comparing the first and second audio files comprises:

matching, by the server, voice samples from at least one of the first and second audio files with a stored voice model.

3. The method of claim 1, wherein comparing the first and second audio files comprises:

extracting, by the server, a first transcription from the first audio file and a second transcription from the second audio file; and

comparing, by the server, the first and second transcriptions to generate the similarity score.

4. The method of claim 1, wherein comparing the first and second audio files comprises:

merging, by the server, the first and second audio files into a third audio file; and

matching, by the server, the third audio file with a stored voice model.

5. The method of claim 1, wherein comparing the first and second audio files comprises:

extracting, by the server, a first set of key words from the first audio file and a second set of keywords from the second audio file; and

comparing, by the server, the first and second sets of keywords to generate the similarity score.

6. The method of claim 1, further comprising:

receiving, by the server, the first audio file in an encrypted form from the first electronic device;

receiving, by the server, the second audio file in an encrypted form from the second electronic device; and

comparing, by the server, the first and second audio files in an encrypted domain to generate the similarity score.

7. The method of claim 1, wherein the first electronic device and second electronic device are used for second factor authentication.

8. The method of claim 1, wherein the first electronic device and second electronic device are used for enrollment.

9. A computer implemented method comprising:

receiving, by a server from a first application in an electronic device, a first audio file of a user'"'"'s voice captured by the first application in response to receiving a voice command from the user;

transmitting, by the server to a second application, a command to trigger the second application to capture the user'"'"'s voice in response to the first application receiving the voice command;

receiving, by the server from the second application in the electronic device, a second audio file of the user'"'"'s voice captured by the second application in response to the second application receiving the command;

comparing, by the server, the first and second audio files to generate a similarity score that determines a likelihood that the first application and the second application captured the user'"'"'s voice at the same time; and

authenticating the user, by the server, in response to the server determining that the similarity score is above a threshold.

10. The method of claim 9, wherein comparing the first and second audio files comprises:

matching, by the server, voice samples from at least one of the first and second audio files with a stored voice model.

11. The method of claim 9, wherein comparing the first and second audio files comprises:

extracting, by the server, a first transcription from the first audio file and a second transcription from the second audio file; and

comparing, by the server, the first and second transcriptions to generate the similarity score.

12. The method of claim 9, wherein comparing the first and second audio files comprises:

merging, by the server, the first and second audio files into a third audio file; and

matching, by the server, the third audio file with a stored voice model.

13. The method of claim 9, wherein comparing the first and second audio files comprises:

extracting, by the server, a first set of key words from the first audio file and a second set of keywords from the second audio file; and

comparing, by the server, the first and second sets of keywords to generate the similarity score.

14. The method of claim 9, further comprising:

receiving, by the server, the first audio file in an encrypted form from the first application;

receiving, by the server, the second audio file in an encrypted form from the second application; and

comparing, by the server, the first and second audio files in an encrypted domain to generate the similarity score.

15. The method of claim 9, wherein the first and second applications are used for second factor authentication.

16. The method of claim 9, wherein the first and second applications are used for enrollment.

17. A system comprising:

a non-transitory storage medium storing a plurality of computer program instructions; and

a processor of a third electronic device electrically coupled to the non-transitory storage medium and configured to execute the plurality of computer program instructions to;

receive from a first electronic device a first audio file of a user'"'"'s voice captured by the first electronic device in response to receiving a voice command from the user;

transmit, by the processor of the third electronic device, to a second electronic device a command to trigger the second electronic device to capture the user'"'"'s voice in response to the first electronic device receiving the voice command;

receive from the second electronic device a second audio file of the user'"'"'s voice captured by the second electronic device in proximity to the first electronic device in response to the second electronic device receiving the command;

compare the first and second audio files to generate a similarity score that determines a likelihood that the first electronic device and the second electronic device captured the user'"'"'s voice at the same time; and

enroll the user to a service in response to the processor determining that the similarity score is above a threshold.

18. The system of claim 17, wherein to compare the first and second audio files, the processor is further configured to execute the plurality of computer program instructions to:

match voice samples from at least one of the first and second audio files with a stored voice model.

19. The system of claim 17, wherein to compare the first and second audio files, the processor is further configured to execute the plurality of computer program instructions to:

extract a first transcription from the first audio file and a second transcription from the second audio file; and

compare the first and second transcriptions to generate the similarity score.

20. The system of claim 17, wherein to compare the first and second audio files, the processor is further configured to execute the plurality of computer program instructions to:

merge the first and second audio files into a third audio file; and

match the third audio file with a stored voice model.

21. A computer-implemented method comprising:

receiving, by a second electronic device in proximity to a first electronic device, from a third electronic device a command to trigger the second electronic device to record a user'"'"'s voice, the command being generated in response to the first electronic device receiving a voice command from the user;

recording, by the second electronic device, the user'"'"'s voice to generate a second audio file in response to the second electronic device receiving the command from the third electronic device;

receiving, by the second electronic device, a first audio file of the user'"'"'s voice recorded by the first electronic device in response to receiving the voice command from the user;

comparing, by the second electronic device, the first and second audio files to generate a similarity score that determines a likelihood that the first electronic device and the second electronic device captured the user'"'"'s voice at the same time; and

transmitting, by the second electronic device, the similarity score to an authentication server such that the authentication server authenticates the user based upon the similarity score.