Transparent voice registration and verification method and system

• US 9,369,577 B2
• Filed: 10/29/2014
• Issued: 06/14/2016
• Est. Priority Date: 07/30/2008
• Status: Active Grant

• Current Assignee: AT&T Alex Holdings LLC (AT&T, Inc.)
• Original Assignee: Interactions, LLC
• Inventors: Gilger, Mazin
• Primary Examiner(s): Gauthier, Gerald
• Application Number:
  US14/526,933
• Publication Number:
  US 20150055764A1
• Time in Patent Office: 594 Days
• Field of Search: 379/88.01, 379/88.02, 379/88.03, 379/88.13, 455/414.1, 704/2, 704/235, 704/256, 704/9, 704/233, 704/240, 704/246, 704/251, 704/275, 713/186, 345/158
• US Class Current: 1/1
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/14 Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
• CPC Class Codes: H04M 2201/36 Memories
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2203/6045 Identity confirmation
• CPC Class Codes: H04M 3/385 using speech signals
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing

Abstract

A method includes receiving a communication from a party at a voice response system and capturing speech spoken by the party during the communication. Then a processor creates a voice model of the party, the voice model being created by processing the speech, without notifying the party. The voice model is then stored to provide voice verification during a subsequent communication.

Claims

1. A method comprising:

providing a party communicating with a voice response system with one or more digital prompts;

capturing speech spoken by the party in response to the one or more digital prompts;

creating, with a processor, a voice model of the party, the voice model being created by processing the speech; and

verifying an identity of the party by applying the voice model to speech spoken by the party during a subsequent communication between the party and the voice response system,

wherein the voice model is created without notifying the party.

2. The method according to claim 1, wherein verifying an identity of the party comprises:

receiving a communication from a requester requesting access to an account;

prompting the requester for information;

capturing speech of the requester;

processing the speech of the requester to create processed speech; and

comparing the processed speech of the requester with the voice model.

3. The method according to claim 2, further comprising determining whether the processed speech and the voice model are a match.

4. The method according to claim 3, further comprising granting access to the account when the processed speech and the voice model match.

5. The method according to claim 3, further comprising denying access to the account when the processed speech and the voice model fail to match.

6. The method according to claim 3, further comprising screening the requester when the processed speech and the voice model fail to match.

7. The method according to claim 3, further comprising automatically updating the voice model when the processed speech and the voice model match.

8. The method according to claim 1, wherein the capturing comprises isolating the speech of the party via a segmentation algorithm.

9. The method according to claim 2, wherein the information comprises account information.

10. The method according to claim 2, further comprising automatically updating the voice model with new voiceprint information.

11. A non-transitory computer-readable storage medium encoded with an executable computer program for registering a voice of a party in order to provide voice verification and that, when executed by a processor, causes the processor to perform operations comprising:

providing a party communicating with a voice response system with one or more digital prompts;

capturing speech spoken by the party in response to the one or more digital prompts;

creating, with a processor, a voice model of the party, the voice model being created by processing the speech; and

verifying an identity of the party by applying the voice model to speech spoken by the party during a subsequent communication between the party and the voice response system,

wherein the voice model is created without notifying the party.

12. The non-transitory computer-readable storage medium according to claim 11, wherein verifying an identity of the party comprises:

receiving a communication from a requester requesting access to an account;

prompting the requester for information;

capturing speech of the requester;

processing the speech of the requester to create processed speech; and

comparing the processed speech of the requester with the voice model.

13. The non-transitory computer-readable storage medium according to claim 12, further comprising determining whether the processed speech and the voice model are a match.

14. The non-transitory computer-readable storage medium according to claim 13, further comprising granting access to the account when the processed speech and the voice model match.

15. The non-transitory computer-readable storage medium according to claim 13, further comprising denying access to the account when the processed speech and the voice model fail to match.

16. The non-transitory computer-readable storage medium according to claim 13, further comprising screening the requester when the processed speech and the voice model fail to match.

17. The non-transitory computer-readable storage medium according to claim 13, further comprising automatically updating the voice model when the processed speech and the voice model match.

18. The non-transitory computer-readable storage medium according to claim 11, wherein the capturing comprises isolating the speech of the party via a segmentation algorithm.

19. The non-transitory computer-readable storage medium according to claim 12, further comprising automatically updating the voice model with new voiceprint information.

20. A system, comprising:

a processor; and

a memory encoded with an executable computer program that, when executed by the processor, causes the processor to perform operations comprising;

providing a party communicating with a voice response system with one or more digital prompts,

capturing speech spoken by the party in response to the one or more digital prompts,

creating, with a processor, a voice model of the party, the voice model being created by processing the speech, and

verifying an identity of the party by applying the voice model to speech spoken by the party during a subsequent communication between the party and the voice response system,

wherein the voice model is created without notifying the party.