Digital signatures for communications using text-independent speaker verification

• US 9,455,983 B2
• Filed: 06/09/2014
• Issued: 09/27/2016
• Est. Priority Date: 12/21/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Bansal, Pradeep K., Begeja, Lee, Creswell, Carroll W., Farah, Jeffrey Joseph, Stern, Benjamin J., Wilpon, Jay
• Primary Examiner(s): Sirjani, Fariba
• Application Number:
  US14/299,874
• Publication Number:
  US 20150073800A1
• Time in Patent Office: 841 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: H04L 63/0823 using certificates cryptographic mechanisms or cryptographic arrangements for entity authentication involving certificates H04L9/3263
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231

Abstract

A speaker-verification digital signature system is disclosed that provides greater confidence in communications having digital signatures because a signing party may be prompted to speak a text-phrase that may be different for each digital signature, thus making it difficult for anyone other than the legitimate signing party to provide a valid signature.

Claims

1. A method comprising:

receiving, from a first device and at a second device, a message prepared by a sender and to be sent to a destination address of a recipient, wherein the message comprises a sender identification, an authentication session request and an invitation to create an authentication certificate for both the sender and the message;

transmitting, from the second device, a session identification and a text prompt for the sender to speak;

receiving, at the second device, an audible response from the sender in response to the text prompt;

confirming an identity of the sender by;

comparing the audible response to a voice template to determine an authenticity of the sender to yield a first comparison, wherein the voice template is chosen based on the sender identification associated with the message;

performing speech recognition on the audible response to extract spoken words;

comparing the spoken words against the text prompt using speaker-independent speech recognition, to yield a second comparison; and

when the first comparison is above a first threshold and the second comparison is above a second threshold, transmitting a speaker-verification digital signature associated with the message to the destination address of the recipient, wherein the recipient can confirm the identity of the sender via receipt of the speaker-verification digital signature as identified by the session identification.

2. The method of claim 1, wherein when a confidence score associated with at least one of the first comparison and the second comparison exceeds a threshold:

generating the authentication certificate; and

packaging the session identification with the authentication certificate.

3. The method of claim 1, wherein the session identification is unique from other sessions with respect to one of:

a communication format, a sender system, and the identity.

4. The method of claim 1, wherein the session identification identifies a type of communication session.

5. The method of claim 1, wherein the voice template is received from a database.

6. A system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising;

receiving, from a first device and at a second device, a message prepared by a sender and to be sent to a destination address of a recipient, wherein the message comprises a sender identification, an authentication session request and an invitation to create an authentication certificate for both the sender and the message;

transmitting, from the second device, a session identification and a text prompt for the sender to speak;

receiving, at the second device, an audible response from the sender in response to the text prompt;

confirming an identity of the sender by;

comparing the audible response to a voice template to determine an authenticity of the sender to yield a first comparison, wherein the voice template is chosen based on the sender identification associated with the message;

performing speech recognition on the audible response to extract spoken words;

comparing the spoken words against the text prompt using speaker-independent speech recognition, to yield a second comparison; and

when the first comparison is above a first threshold and the second comparison is above a second threshold, transmitting a speaker-verification digital signature associated with the message to the destination address of the recipient, wherein the recipient can confirm the identity of the sender via receipt of the speaker-verification digital signature as identified by the session identification.

7. The system of claim 6, wherein when a confidence score associated with at least one of the first comparison and the second comparison exceeds a threshold:

generating the authentication certificate; and

packaging the session identification with the authentication certificate.

8. The system of claim 6, wherein the session identification is unique from other sessions with respect to one of:

a communication format, a sender system, and the identity.

9. The system of claim 6, wherein the session identification identifies a type of communication session.

10. The system of claim 6, wherein the voice template is received from a database.

11. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:

receiving, from a first device and at a second device, a message prepared by a sender and to be sent to a destination address of a recipient, wherein the message comprises a sender identification, an authentication session request and an invitation to create an authentication certificate for both the sender and the message;

transmitting, from the second device, a session identification and a text prompt for the sender to speak;

receiving, at the second device, an audible response from the sender in response to the text prompt;

confirming an identity of the sender by;

comparing the audible response to a voice template to determine an authenticity of the sender to yield a first comparison, wherein the voice template is chosen based on the sender identification associated with the message;

performing speech recognition on the audible response to extract spoken words;

comparing the spoken words against the text prompt using speaker-independent speech recognition, to yield a second comparison; and

when the first comparison is above a first threshold and the second comparison is above a second threshold, transmitting a speaker-verification digital signature associated with the message to the destination address of the recipient, wherein the recipient can confirm the identity of the sender via receipt of the speaker-verification digital signature as identified by the session identification.

12. The computer-readable storage device of claim 11, wherein when a confidence score associated with at least one of the first comparison and the second comparison exceeds a threshold:

generating the authentication certificate; and

packaging the session identification with the authentication certificate.

13. The computer-readable storage device of claim 11, wherein the session identification is unique from other sessions with respect to one of:

a communication format, a sender system, and the identity.

14. The computer-readable storage device of claim 11, wherein the session identification identifies a type of communication session.