Method, apparatus, and program for certifying a voice profile when transmitting text messages for synthesized speech
View Patent ↗A mechanism is provided for authenticating and using a personal voice profile. The voice profile may be issued by a trusted third party, such as a certification authority. The personal voice profile may include information for generating a digest or digital signature for text messages. A speech synthesis system may speak the text message using the voice characteristics, such as prosodic characteristics, only if the voice profile is authenticated and the text message is valid and free of tampering.
1. A system comprising:
a processor configured to execute a method comprising:
encrypting a voice profile to form an encrypted voice profile, wherein the voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual,
generating a message digest of a text message using an algorithm for signing messages,
encrypting the message digest using a private key associated with a public key to form an encrypted message digest, and
outputting the text message, the encrypted voice profile, and the encrypted message digest.
2. The system of claim 1 , wherein the voice profile further comprises at least one of a unique identifier, an expiration for the voice profile, and personal information regarding the individual.
3. The system of claim 1 , wherein the outputting comprises one of storing the text message, the encrypted voice profile, and the encrypted message digest on a computer-readable medium and sending the text message, the encrypted voice profile, and the encrypted message digest to a recipient over a network.
4. The system of claim 1 , wherein the voice profile is digitally signed by a trusted third party.
5. A system comprising:
a processor configured to execute a method comprising:
receiving a text message, an encrypted voice profile, and an encrypted message digest,
decrypting the encrypted voice profile to form a decrypted voice profile, wherein the decrypted voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual,
decrypting the encrypted message digest using a public key to form a decrypted message digest,
generating a message digest of the text message using an algorithm for signing messages, and
responsive to a determination that the decrypted message digest and the message digest match, generating synthesized speech for the text message using the personal prosodic voice characteristic information.
6. The system of claim 5 , wherein the receiving comprises one of retrieving the text message, the encrypted voice profile and the encrypted message digest from a computer-readable medium, and receiving the text message, the encrypted voice profile, and the encrypted message digest from a source over a network.
7. The system of claim 5 , wherein the voice profile further comprises an expiration for the voice profile, and the method further comprises determining whether the voice profile is expired based on the expiration.
8. The system of claim 7 , wherein the synthesized speech generated only if it is determined that the voice profile is not expired.
9. The system of claim 5 , wherein the decrypted voice profile is digitally signed by a trusted third party.
10. At least one computer-readable recordable storage medium storing processor-executable instructions that, when executed by a processor, perform a method comprising:
encrypting a voice profile to form an encrypted voice profile, wherein the voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual;
generating a message digest of a text message using an algorithm for signing messages;
encrypting the message digest using a private key associated with a public key to form an encrypted message digest; and
outputting the text message, the encrypted voice profile, and the encrypted message digest.
11. The at least one computer-readable recordable storage medium of claim 10 , wherein the voice profile further comprises at least one of a unique identifier, an expiration for the voice profile, and personal information regarding the individual.
12. The at least one computer-readable recordable storage medium of claim 10 , wherein the outputting comprises one of storing the text message, the encrypted voice profile, and the encrypted message digest on a computer-readable medium and sending the text message, the encrypted voice profile, and the encrypted message digest to a recipient over a network.
13. The at least one computer-readable recordable storage medium of claim 10 , wherein the voice profile is digitally signed by a trusted third party.
14. At least one computer-readable recordable storage medium storing processor-executable instructions that, when executed by a processor, perform a method comprising:
receiving a text message, an encrypted voice profile, and an encrypted message digest;
decrypting the encrypted voice profile to form a decrypted voice profile, wherein the decrypted voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual;
decrypting the encrypted message digest using a public key to form a decrypted message digest;
generating a message digest of the text message using an algorithm for signing messages; and
responsive to a determination that the decrypted message digest and the message digest match, generating synthesized speech for the text message using the personal prosodic voice characteristic information.
15. The at least one computer-readable recordable storage medium of claim 14 , wherein the receiving comprises one of retrieving the text message, the encrypted voice profile and the encrypted message digest from a computer-readable medium, and receiving the text message, the encrypted voice profile and the encrypted message digest from a source over a network.
16. The at least one computer-readable recordable storage medium of claim 14 , wherein the voice profile further comprises an expiration for the voice profile, and the method further comprises determining whether the voice profile is expired based on the expiration.
17. The at least one computer-readable recordable storage medium of claim 14 , wherein the synthesized speech generated only if it is determined that the voice profile is not expired.
18. The at least one computer-readable recordable storage medium of claim 14 , wherein the decrypted voice profile is digitally signed by a trusted third party.
19. A method comprising:
encrypting a voice profile to form an encrypted voice profile, wherein the voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual;
generating a message digest of a text message using an algorithm for signing messages;
encrypting the message digest using a private key associated with a public key to form an encrypted message digest; and
outputting the text message, the encrypted voice profile, and the encrypted message digest.
20. The method of claim 19 , wherein the voice profile further comprises at least one of a unique identifier, an expiration for the voice profile, and personal information regarding the individual.
21. The method of claim 19 , wherein the outputting comprises one of storing the text message, the encrypted voice profile, and the encrypted message digest on a computer-readable medium and sending the text message, the encrypted voice profile, and the encrypted message digest to a recipient over a network.
22. The method of claim 19 , wherein the voice profile is digitally signed by a trusted third party.
23. A method comprising:
receiving a text message, an encrypted voice profile, and an encrypted message digest;
decrypting the encrypted voice profile to form a decrypted voice profile, wherein the decrypted voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual;
decrypting the encrypted message digest using a public key to form a decrypted message digest;
generating a message digest of the text message using an algorithm for signing messages; and
responsive to a determination that the decrypted message digest and the message digest match, generating synthesized speech for the text message using the personal prosodic voice characteristic information.
24. The method of claim 23 , wherein the receiving comprises one of retrieving the text message, the encrypted voice profile and the encrypted message digest from a computer-readable medium, and receiving the text message, the encrypted voice profile and the encrypted message digest from a source over a network.
25. The method of claim 23 , wherein the voice profile further comprises an expiration for the voice profile, and the method further comprises determining whether the voice profile is expired.
26. The method of claim 25 , wherein the synthesized speech generated only if it is determined that the voice profile is not expired.
27. The method of claim 23 , wherein the decrypted voice profile is digitally signed by a trusted third party.
28. The system of claim 1 , wherein the voice profile further comprises the public key and an identifier of the algorithm for signing messages.
29. The system of claim 5 , wherein the decrypted voice profile further comprises the public key and an identifier of the algorithm for signing messages.
30. The at least one computer-readable recordable storage medium of claim 10 , wherein the voice profile further comprises the public key and an identifier of the algorithm for signing messages.
31. The at least one computer-readable recordable storage medium of claim 14 , wherein the decrypted voice profile further comprises the public key and an identifier of the algorithm for signing messages.
32. The method of claim 19 , wherein the voice profile further comprises the public key and an identifier of the algorithm for signing messages.
33. The method of claim 23 , wherein the decrypted voice profile further comprises the public key and an identifier of the algorithm for signing messages.
34. A system comprising:
a processor configured to:
encrypt a voice profile to form an encrypted voice profile, wherein the voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual; and
output the encrypted voice profile.
35. A system comprising:
a processor configured to:
receive a text message, an encrypted voice profile; and
decrypt an encrypted voice profile to form a decrypted voice profile, wherein the decrypted voice profile comprises personal prosodic voice characteristic information obtained from an individual, the personal prosodic voice characteristic information capable of being used to synthesize speech that sounds like the individual.