Method and system for providing synthesized speech

• US 20050267756A1
• Filed: 05/26/2004
• Published: 12/01/2005
• Est. Priority Date: 05/26/2004
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Business Global LLC (Verizon Communications Inc.)
• Inventors: Sartini, Robert A., Schultz, Paul T.
• Granted Patent: US 7,653,542 B2
• Time in Patent Office: Days
• US Class Current: 704/258
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

An approach providing the efficient use of speech synthesis in rendering text content as audio in a communications network. The communications network can include a telephony network and a data network in support of, for example, Voice over Internet Protocol (VoIP) services. A speech synthesis system receives a text string from either a telephony network, or a data network. The speech synthesis system determines whether a rendered audio file of the text string is stored in a database and to render the text string to output the rendered audio file, if the rendered audio is determined not to exist. The rendered audio file is stored in the database for re-use according to a hash value generated by the speech synthesis system based on the text string.

Claims

1. A method for providing speech synthesis, the method comprising:

receiving a text string;

determining whether a rendered audio file of the text string exists; and

if the rendered audio file does not exist, creating an audio file rendering of the text string, wherein the audio file is stored for retrieval upon subsequent receipt of the text string.

2. A method according to claim 1, further comprising:

generating a unique identifier derived from the received text string according to a predetermined operation, wherein the stored rendered audio file is identified based on the unique identifier.

3. A method according to claim 2, wherein the stored rendered audio file has a file name as the unique identifier.

4. A method according to claim 2, further comprising:

generating a text file containing the text string, wherein the text file has a file name as the unique identifier.

5. A method according to claim 2, wherein the predetermined operation is a hash function, the unique identifier being a hash index.

6. A method according to claim 1, wherein the text string is received from one of a voice response unit, a data network, and a circuit switched telephone network, the method further comprising:

transmitting the rendered audio file to the voice response unit.

7. A method according to claim 1, wherein the text string is received from a web-based application resident on a host, the method further comprising:

transmitting the rendered audio file to the host over a data network.

8. A method according to claim 1, the method further comprising:

generating a reference to the rendered audio file for access via a web-based interface.

9. A system for providing speech synthesis, the system comprising:

a communication interface configured to receive a text string;

a processor configured to determine whether a rendered audio file of the text string is stored in a database; and

speech synthesis logic configured to render the text string to output the rendered audio file if the rendered audio is determined not to exist,

wherein the rendered audio file is stored in the database for retrieval upon subsequent receipt of the text string.

10. A system according to claim 9, wherein the speech synthesis logic is further configured to generate a unique identifier derived from the received text string according to a predetermined operation, wherein the stored rendered audio file is identified based on the unique identifier.

11. A system according to claim 10, wherein the stored rendered audio file has a file name as the unique identifier.

12. A system according to claim 10, wherein the processor generates a text file containing the text string, wherein the text file has a file name as the unique identifier.

13. A system according to claim 10, wherein the predetermined operation is a hash function, the unique identifier being a hash index.

14. A system according to claim 9, wherein the text string is received from a voice response unit.

15. A system according to claim 9, wherein the text string is received from a web-based application resident on a host.

16. A system according to claim 9, the speech synthesis logic is further configured to generate a reference to the rendered audio file for access via a web-based interface.

17. A computer-readable medium carrying one or more sequences of one or more instructions for providing speech synthesis, the one or more sequences of one or more instructions including instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of:

receiving a text string;

determining whether a rendered audio file of the text string exists; and

if the rendered audio file does not exist, creating an audio file rendering of the text string,

wherein the audio file is stored for retrieval upon subsequent receipt of the text string.

18. A computer-readable medium according to claim 17, further including instructions for causing the one or more processors to perform the step of:

generating a unique identifier derived from the received text string according to a predetermined operation, wherein the stored rendered audio file is identified based on the unique identifier.

19. A computer-readable medium according to claim 18, wherein the stored rendered audio file has a file name as the unique identifier.

20. A computer-readable medium according to claim 18, further including instructions for causing the one or more processors to perform the step of:

generating a text file containing the text string, wherein the text file has a file name as the unique identifier.

21. A computer-readable medium according to claim 18, wherein the predetermined operation is a hash function, the unique identifier being a hash index.

22. A computer-readable medium according to claim 17, wherein the text string is received from one of a voice response unit, a data network, and a circuit switched telephone network, the computer-readable medium further including instructions for causing the one or more processors to perform the step of:

initiating transmission of the rendered audio file to the voice response unit.

23. A computer-readable medium according to claim 17, wherein the text string is received from a web-based application resident on a host, the computer-readable medium further including instructions for causing the one or more processors to perform the step of:

initiating transmission of the rendered audio file to the host over a data network.

24. A computer-readable medium according to claim 17, further including instructions for causing the one or more processors to perform the step of:

generating a reference to the rendered audio file for access via a web-based interface.

25. A system for providing speech synthesis in a communications network including a telephony network and a data network, the system comprising:

a speech synthesis node configured to receive a text string from one of the telephony network and the data network, the speech synthesis node being further configured to determine whether a rendered audio file of the text string is stored in a database and to render the text string to output the rendered audio file if the rendered audio is determined not to exist,

wherein the rendered audio file is stored in the database for re-use according to a hash value generated by the speech synthesis node based on the text string.

26. A system according to claim 25, further comprising:

a server configured to provide access via a web-based interface to the stored rendered audio file.

27. A system according to claim 25, further comprising:

a voice response unit in communication with the telephony network and configured to generate the text string.