System and method for text-to-speech processing in a portable device

• US 20040210439A1
• Filed: 12/23/2003
• Published: 10/21/2004
• Est. Priority Date: 04/18/2003
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Schrocter, Horst Juergen
• Granted Patent: US 7,013,282 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/047 Architecture of speech synthesisers

Abstract

A system and method for providing high-quality text-to-speech (TTS) output in a low-complexity device is disclosed. TTS output is generated by a TTS system that resides on a high-complexity device. The TTS output is transmitted from the high-complexity device to the low-complexity device for subsequent retrieval and playback.

Claims

1. A method for synthesizing speech on a portable device, comprising:

(1) receiving presynthesized slot information as part of a synchronization process with a computing device, wherein said slot information represents a value of a defined data type in a user record on said computing device, said slot information being designed for inclusion at a predefined position within a carrier phrase;

(2) storing said presynthesized slot information in a memory; and

(3) reproducing said carrier phrase and said presynthesized slot information as audible output for a user.

2. The method of claim 1, wherein said slot information is one of a name, number, and location.

3. The method of claim 1, further comprising receiving a presynthesized carrier phrase.

4. The method of claim 1, wherein said carrier phrase and said presynthesized slot information is compressed and wherein said reproducing comprises passing said carrier phrase and said presynthesized slot information through a codec.

5. The method of claim 1, wherein said receiving comprises receiving via a wired link.

6. The method of claim 1, wherein said receiving comprises receiving via a wireless link.

7. A method for synthesizing speech, comprising:

(1) presynthesizing a portion of speech using a text analysis module and a speech synthesis module; and

(2) transmitting the presynthesized portion of speech to a portable device for storage in the portable device, wherein the storage of a plurality of presynthesized portions of speech enables the portable device to provide a text-to-speech application.

8. The method of claim 7, wherein said presynthesizing comprises presynthesizing using a concatenative text-to-speech process.

9. The method of claim 7, wherein the speech processing system is a computer.

10. The method of claim 7, wherein said transmitting comprises transmitting via a wired link.

11. The method of claim 7, wherein said transmitting comprises transmitting via a wireless link.

12. The method of claim 7, wherein said transmitting comprises transmitting the presynthesized portion of speech to a portable device.

13. The method of claim 7, wherein said transmitting comprises transmitting the presynthesized portion of speech to a personal digital assistant.

14. The method of claim 7, wherein said transmitting comprises transmitting the presynthesized portion as part of a synchronization process between the speech processing system and the portable device.

15. The method of claim 7, wherein said transmitting comprises transmitting presynthesized carrier segments and presynthesized slot segments.

16. The method of claim 15, wherein said slot segments includes one of name, location and number information.

17. A speech processing method on a portable computing device, comprising:

(1) receiving presynthesized speech from a speech processing system;

(2) storing the received presynthesized speech in a memory;

(3) retrieving one or more presynthesized speech segments from memory, the one or more retrieved presynthesized speech segments corresponding to a text message that is to be communicated to a user; and

(4) outputting said one or more retrieved presynthesized speech segments as audio output.

18. The method of claim 17, wherein said receiving comprises receiving via a wired link.

19. The method of claim 18, wherein said receiving comprises receiving via a wireless link.

20. The method of claim 17, wherein said receiving comprises receiving during a synchronization process with a personal computer.

21. The method of claim 17, wherein said retrieving comprises retrieving one or more carrier segments and slot segments.

22. The method of claim 21, wherein said slot segments includes one of name and number information.

23. The method of claim 17, wherein said receiving comprises receiving presynthesized speech generated using a concatenative text-to-speech process.

24. The method of claim 17, wherein said one or more presynthesized speech segments are uncompressed.

25. The method of claim 17, wherein said one or more presynthesized speech segments are compressed.

26. The method of claim 17, wherein said one or more presynthesized speech segments are dynamic content.

27. The method of claim 26, wherein said dynamic content is one of an email, instant message, stock alert, and breaking news.

28. A computer-readable medium that stores a program for controlling a computer device to perform a method in a speech processing system that includes a speech synthesis module that enables a conversion of text into synthesized speech, the method comprising:

(1) presynthesizing a portion of speech using the text analysis module and the speech synthesis module; and

(2) transmitting the presynthesized portion of speech to a portable device for storage in the portable device, wherein the storage of a plurality of presynthesized portions of speech enables the portable device to provide a text-to-speech application.

29. A system for synthesizing speech, comprising:

means for presynthesizing a portion of speech using a text analysis module and a speech synthesis module; and

means for transmitting the presynthesized portion of speech to a portable device for storage in the portable device, wherein the storage of a plurality of presynthesized portions of speech enables the portable device to provide a text-to-speech application.