Secure text-to-speech synthesis in portable electronic devices

• US 9,166,977 B2
• Filed: 12/22/2011
• Issued: 10/20/2015
• Est. Priority Date: 12/22/2011
• Status: Active Grant

• Current Assignee: Malikie Innovations Limited (Key Patent Innovations Limited)
• Original Assignee: Blackberry Limited
• Inventors: Adams, Neil Patrick, Desai, Simon Peter
• Primary Examiner(s): MOORTHY, ARAVIND K
• Application Number:
  US13/335,616
• Publication Number:
  US 20130166915A1
• Time in Patent Office: 1,398 Days
• Field of Search: 713/176, 713/168, 713/186, 726/5, 726/26, 382/115
• US Class Current: 1/1
• 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: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G07C 9/25 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: H04L 2209/80 Wireless network architectures or network communication protocols for wireless network security H04W12/00
• CPC Class Codes: H04L 63/08 for authentication of entities cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32
• 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
• CPC Class Codes: H04L 63/126 the source of the received data
• CPC Class Codes: H04L 9/321 involving a third party or a trusted authority
• CPC Class Codes: H04L 9/3247 involving digital signatures
• CPC Class Codes: H04L 9/3263 involving certificates, e.g. public key certificate [PKC] or attribute certificate [AC]; Public key infrastructure [PKI] arrangements network architectures or network communication protocols for supporting authentication of entities using certificates in a packet data network H04L63/0823

Abstract

A method for secure text-to-speech conversion of text using speech or voice synthesis that prevents the originator'"'"'s voice from being used or distributed inappropriately or in an unauthorized manner is described. Security controls authenticate the sender of the message, and optionally the recipient, and ensure that the message is read in the originator'"'"'s voice, not the voice of another person. Such controls permit an originator'"'"'s voiceprint file to be publicly accessible, but limit its use for voice synthesis to text-based content created by the sender, or sent to a trusted recipient. In this way a person can be assured that their voice cannot be used for content they did not write.

Claims

1. A method of secure text-to-speech conversion, the method comprising, at a computing device:

receiving, from an originator, a voiceprint and a list of trusted recipients;

receiving, from a recipient, text-based content, provided to the recipient by the originator, and a digital signature of the recipient;

in accordance with the digital signature of the recipient, verifying that the recipient is listed in the list of trusted recipients; and

when the recipient is listed in the list of trusted recipients, converting, in accordance with the voiceprint, at least a portion of the text-based content to an audio format to obtain converted text-based content, for output to the recipient.

2. The method of claim 1, wherein verifying that the recipient is listed in the list of trusted recipients is preceded by verifying the digital signature of the recipient.

3. The method of claim 1, further comprising transferring the converted text-based content to the recipient.

4. The method of claim 1 further comprising:

receiving, from the originator, a digital certificate of the originator; and

receiving, from the recipient, a signature of the originator, provided to the recipient by the originator, with the text-based content.

5. The method of claim 4, further comprising verifying the signature of the originator against the digital certificate of the originator.

6. The method of claim 5 further comprising, when the signature of the originator compares with the digital certificate of the signature, verifying the status of the digital certificate.

7. The method of claim 6, wherein converting, in accordance with the voiceprint, at least a portion of the text-based content to an audio format to obtain converted text-based content, for output to the recipient, is performed when the status of the digital certificate is valid.

8. The method of claim 1, wherein the voiceprint permits synthesis of the originator'"'"'s speech.

9. The method of claim 8, wherein the voiceprint uses hidden Markov models of the originator'"'"'s voice characteristics.

10. A server for providing secure text-to-speech conversion, the server comprising:

a hardware processor capable of;

receiving, from an originator, a voiceprint and a list of trusted recipients;

receiving, from a recipient, text-based content, provided to the recipient by the originator, and a digital signature of the recipient;

in accordance with the digital signature of the recipient, verifying that the recipient is listed in the list of trusted recipients; and

when the recipient is listed in the list of trusted recipients, converting, in accordance with the voiceprint, at least a portion of the text-based content to an audio format to obtain converted text-based content, for output to the recipient.

11. The server of claim 10, wherein verifying that the recipient is listed in the list of trusted recipients is preceded by verifying the digital signature of the recipient.

12. The server of claim 10, wherein the hardware processor is capable of transferring the converted text-based content to the recipient.

13. The server of claim 10, wherein the hardware processor is further capable of:

receiving, from the originator, a digital certificate of the originator; and

receiving, from the recipient, a signature of the originator, provided to the recipient by the originator, with the text-based content.

14. The server of claim 13, wherein the hardware processor is further capable of verifying the signature of the originator against the digital certificate of the originator.

15. The server of claim 14, wherein the hardware processor is further capable of, when the signature of the originator compares with the digital certificate of the signature, verifying the status of the digital certificate.

16. The server of claim 15 wherein, when the status of the digital certificate is valid, the hardware processor is capable of converting, in accordance with the voiceprint, at least a portion of the text-based content to an audio format to obtain converted text-based content, for output to the recipient.

17. The server of claim 10, wherein the voiceprint permits synthesis of the originator'"'"'s speech.

18. The server of claim 10, wherein the voiceprint uses hidden Markov models of the originator'"'"'s voice characteristics.

19. A portable electronic device capable of providing secure text-to-speech conversion, the device comprising:

a hardware processor capable of;

obtaining an encrypted voiceprint, the encrypted voiceprint being associated to an originator;

obtaining text-based content from the originator;

authenticating the originator;

when the originator has been authenticated, decrypting the encrypted voiceprint to obtain a decrypted voiceprint;

converting at least a portion of the text-based content to an audio format in accordance with the decrypted voiceprint; and

causing the audio format to be output to a sound output device.

20. The device of claim 19, wherein authenticating includes verifying a digital signature of the originator.

21. The device of claim 19, wherein authenticating includes authenticating in accordance with a digital certificate accompanying the text-based content.

22. The device of claim 19, further comprising a memory capable of storing the encrypted voiceprint as an encrypted file.

23. The device of claim 22, wherein, to access the decrypted voiceprint, the hardware processor is capable of retrieving the encrypted file and a shared key, and of decrypting the encrypted file with the shared key.

24. The device of claim 19, wherein the decrypted voiceprint permits synthesis of the originator'"'"'s voice.

25. The device of claim 19, wherein the decrypted voiceprint uses hidden Markov models of the originator'"'"'s voice characteristics.

26. A non-transitory computer-readable medium having recorded thereon instructions to be carried out by a computing device to:

receive, from an originator, a voiceprint and a list of trusted recipients;

receive, from a recipient, text-based content, provided to the recipient by the originator, and a digital signature of the recipient;

in accordance with the digital signature of the recipient, verify that the recipient is listed in the list of trusted recipients; and

when the recipient is listed in the list of trusted recipients, convert, in accordance with the voiceprint, at least a portion of the text-based content to an audio format to obtain converted text-based content, for output to the recipient.

27. The non-transitory computer-readable medium of claim 26 wherein the instructions comprise additional instructions to be carried out by the computing device to verify the digital signature of the recipient prior to verifying that the recipient is listed in the list of trusted recipients.

28. The non-transitory computer-readable medium of claim 26 wherein the instructions comprise additional instructions to be carried out by the computing device to transfer the converted text-based content to the recipient.

29. The non-transitory computer-readable medium of claim 26 wherein the instructions comprise additional instructions to be carried out by the computing device to:

receive, from the originator, a digital certificate of the originator; and

receive, from the recipient, a signature of the originator, provided to the recipient by the originator, with the text-based content.

30. The non-transitory computer-readable medium of claim 29 wherein the instructions comprise further instructions to be carried out by the computing device to verify the signature of the originator against the digital certificate of the originator.

31. The non-transitory computer-readable medium of claim 30 wherein the instructions comprise supplemental instructions to be carried out by the computing device to, when the signature of the originator compares with the digital certificate of the signature, verify the status of the digital certificate.

32. The non-transitory computer-readable medium of claim 26 wherein the voiceprint permits synthesis of the originator'"'"'s speech.

33. The non-transitory computer-readable medium of claim 32 wherein the voiceprint uses hidden Markov models of the originator'"'"'s voice characteristics.