Text-to-speech conversion system on an integrated circuit

• US 6,959,279 B1
• Filed: 03/26/2002
• Issued: 10/25/2005
• Est. Priority Date: 03/26/2002
• Status: Expired due to Fees

• Current Assignee: Winbond Electronics Corporation
• Original Assignee: Winbond Electronics Corporation
• Inventors: Yang, Bor-Wen, Chen, Wen-Kuei, Chang, Ming-Bing, Wu, Bo-Hung, Doan, Rodney Lee, Holzmann, Peter J., Raina, Aditya, Awsare, Saleel V., Lin, Chuan-Shin Rick, Jackson, Geoffrey Bruce
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US10/108,766
• Time in Patent Office: 1,309 Days
• Field of Search: 704/258, 704/260, 704/266, 704/267, 704/268, 704/269, 365/45, 369/63, 369/64
• US Class Current: 704/258
• CPC Class Codes: G10L 13/047 Architecture of speech synthesisers

Abstract

A text-to-speech conversion system that includes a first module to convert text into words, a second module to convert words into phonemes, a third module to map phonemes to sound units, and a storage unit to store speech representations for a library of sound units. The first, second, and third modules and the storage unit are implemented within a single integrated circuit to reduce size and cost. The system typically further includes a ROM to store the codes for the modules, a RAM to store the text and intermediate results, a processor to execute the codes for the modules, a control module to direct the operation of the first, second, and third modules. The storage unit may be implemented with a multi-level, non-volatile analog storage array and may be programmed with a new library of speech representations by a programming module.

Claims

1. A text-to-speech conversion system comprising:

a first module operative to convert text into words;

a second module operative to convert words into phonemes;

a third module operative to map phonemes into sound units; and

a storage unit operative to store analog speech representations for a library of sound units, and

wherein the first, second, and third modules and the storage unit are implemented within a single integrated circuit.

2. The system of claim 1, further comprising:

a control module operative to direct operations of the first, second, and third modules.

3. The system of claim 1, further comprising:

a processor operative to execute codes for the first, second, and third modules.

4. The system of claim 3, further comprising:

a non-volatile storage unit configured to store the codes for the first, second, and third modules.

5. The system of claim 3, further comprising:

a volatile storage unit configured to store the text to be converted to speech.

6. The system of claim 1, wherein the storage unit is a multi-level, non-volatile analog storage array.

7. The system of claim 1, wherein the storage unit is configured to store the analog speech representations for naturally spoken word parts that are stored as the library of sound units.

8. The system of claim 1, wherein the storage unit is configured to store a library of analog speech representations for the library of sound units for a selected language.

9. The system of claim 8, wherein the library includes at least one million analog speech representations.

10. The system of claim 8, further comprising:

a programming module operable to direct programming of a new library of analog speech representations for a new language into the storage unit.

11. The system of claim 8, wherein each sound unit corresponds to a valid analog speech representation stored in the storage unit.

12. The system of claim 1, further comprising:

a plurality of queues, one queue for each of the first, second, and third modules, wherein each queue is configured to store outputs from the associated module.

13. The system of claim 1, wherein the third module is operative to provide, for each sound unit, an address indicative of a location in the storage unit and the duration for a corresponding analog speech representation.

14. The system of claim 1, further comprising:

an input data buffer operative to store the text to be converted to speech; and

a command buffer operative to store commands to be processed by the system.

15. The system of claim 1, further comprising:

an interface unit operative to provide a serial interface between the system and external units.

16. The system of claim 1, further comprising:

a coder/decoder operative to convert an analog output of the storage unit into a digital format.

17. The system of claim 1, wherein the text is provided in an ASCII format.

18. An integrated circuit comprising:

a volatile storage unit configured to store text;

a non-volatile storage unit configured to store codes for a plurality of modules used to convert the text to speech;

a processor operative to execute the codes for the plurality of modules; and

a storage unit operative to store a library of analog speech representations, each analog speech representation being stored in an uncompressed analog format.

19. The integrated circuit of claim 18, wherein the plurality of modules include

a first module operative to convert the text into words,

a second module operative to convert the words into phonemes, and

a third module operative to map the phonemes into analog speech representations.

20. The integrated circuit of claim 18, further comprising:

a serial interface unit operative to provide an interface between the integrated circuit and external units.

21. The integrated circuit of claim 18, further comprising:

a programming control unit operable to direct programming of a new library of analog speech representations into the storage unit.

22. The integrated circuit of claim 18, wherein the storage unit is a multi-level, non-volatile analog storage array.

23. An integrated circuit comprising:

means for storing text;

means for storing codes for a plurality of modules used to convert the text to speech;

means for executing the codes for the plurality of modules; and

means for storing a library of analog speech representations, each analog speech representation being stored in an uncompressed analog format.

24. The integrated circuit of claim 23, wherein the plurality of modules include

a first module operative to convert the text into words,

a second module operative to convert the words into phonemes, and

a third module operative to map the phonemes into analog speech representations.