Digital signatures for communications using text-independent speaker verification
View Patent ↗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.
1. A method comprising, performing at an authentication service system:
receiving an authentication session invitation request from a sender of an email, wherein the email is sent to a destination address of a recipient, and wherein the authentication session invitation comprises an email address of the sender and an invitation to create an authentication certificate for the sender and the email;
sending, to the sender, a session identification and a text-phrase prompt comprising a text phrase;
receiving, from the sender in response the text-phrase prompt, the destination address of the recipient and an audio signal;
retrieving, based on the email address of the sender, a voice template associated with the sender;
comparing the audio signal to the voice template, to yield a confidence score;
when the confidence score exceeds a threshold:
generating the authentication certificate; and
packaging the session identification with the authentication certificate, to yield authentication information;
when the confidence score does not exceed the threshold, packaging the session identification and the confidence score as the authentication information; and
transmitting the authentication information to the destination email address of the recipient.
2. The method of claim 1 , wherein the authenticating further comprises:
generating the text phrase; and
transmitting the text phrase to the sender prior to receiving the audio signal from the sender.
3. The method of claim 1 , wherein comparing the audio signal to the voice template further comprises:
performing speech recognition on the audio signal to extract spoken words;
generating a first confidence score by comparing the spoken words against the text phrase;
extracting features from the audio signal;
generating a second confidence score by comparing the features against the voice template; and
combining the first confidence score and the second confidence score to generate the confidence score.
4. 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 claimed identity.
5. The method of claim 1 , wherein the session identification identifies a type of communication session.
6. The method of claim 1 , wherein the voice template is received from a database.
7. 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 being performed at an authentication service system, the operations comprising:
receiving an authentication session invitation request from a sender of an email, wherein the email is sent to a destination address of a recipient, and wherein the authentication session invitation comprises an email address of the sender and an invitation to create an authentication certificate for the sender and the email;
sending, to the sender, a session identification and a text-phrase prompt comprising a text phrase;
receiving, from the sender in response the text-phrase prompt, the destination address of the recipient and an audio signal;
retrieving, based on the email address of the sender, a voice template associated with the sender;
comparing the audio signal to the voice template, to yield a confidence score;
when the confidence score exceeds a threshold:
generating the authentication certificate; and
packaging the session identification with the authentication certificate, to yield authentication information;
when the confidence score does not exceed the threshold, packaging the session identification and the confidence score as the authentication information; and
transmitting the authentication information to the destination email address of the recipient.
8. The system of claim 7 , wherein the authenticating further comprises:
generating the text phrase; and
transmitting the text phrase to the sender prior to receiving the audio signal from the sender.
9. The system of claim 7 , wherein comparing the audio signal to the voice template further comprises:
performing speech recognition on the audio signal to extract spoken words;
generating a first confidence score by comparing the spoken words against the text phrase;
extracting features from the audio signal;
generating a second confidence score by comparing the features against the voice template; and
combining the first confidence score and the second confidence score to generate the confidence score.
10. The system of claim 7 , wherein the session identification is unique from other sessions with respect to one of: a communication format, a sender system, and the claimed identity.
11. The system of claim 7 , wherein the session identification identifies a type of communication session.
12. The system of claim 7 , wherein the voice template is received from a database.
13. A computer-readable storage device having instructions stored which, when executed by a processor of an authentication service system, cause the processor to perform operations comprising:
receiving an authentication session invitation request from a sender of an email, wherein the email is sent to a destination address of a recipient, and wherein the authentication session invitation comprises an email address of the sender and an invitation to create an authentication certificate for the sender and the email;
sending, to the sender, a session identification and a text-phrase prompt comprising a text phrase;
receiving, from the sender in response the text-phrase prompt, the destination address of the recipient and an audio signal;
retrieving, based on the email address of the sender, a voice template associated with the sender;
comparing the audio signal to the voice template, to yield a confidence score;
when the confidence score exceeds a threshold:
generating the authentication certificate; and
packaging the session identification with the authentication certificate, to yield authentication information;
when the confidence score does not exceed the threshold, packaging the session identification and the confidence score as the authentication information; and
transmitting the authentication information to the destination email address of the recipient.
14. The computer-readable storage device of claim 13 , wherein the authenticating further comprises:
generating the text phrase; and
transmitting the text phrase to the sender prior to receiving the audio signal from the sender.
15. The computer-readable storage device of claim 13 , wherein comparing the audio signal to the voice template further comprises:
performing speech recognition on the audio signal to extract spoken words;
generating a first confidence score by comparing the spoken words against the text phrase;
extracting features from the audio signal;
generating a second confidence score by comparing the features against the voice template; and
combining the first confidence score and the second confidence score to generate the confidence score.
16. The computer-readable storage device of claim 13 , wherein the session identification is unique from other sessions with respect to one of: a communication format, a sender system, and the claimed identity.
17. The computer-readable storage device of claim 13 , wherein the session identification identifies a type of communication session.