Method and apparatus for word pronunciation composition

• US 20030088415A1
• Filed: 11/07/2001
• Published: 05/08/2003
• Est. Priority Date: 11/07/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Reich, David E., Lucas, Bruce D., Kobal, Jeffrey S.
• Granted Patent: US 7,099,828 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method of generating pronunciation information can include graphically presenting at least one activatable visual identifier corresponding to individual ones of a plurality of phonemes. Responsive to a selection of one of the visual identifiers, pronunciation information can be generated in accordance with the selected visual identifier. The pronunciation information can be compiled responsive to a selection of one of the plurality of visual identifiers.

Claims

1. A method of generating pronunciation information comprising:

graphically presenting at least one activatable visual identifier corresponding to individual ones of a plurality of phonemes;

responsive to a selection of one of said visual identifiers, generating said pronunciation information in accordance with said selected visual identifier; and

compiling said pronunciation information responsive to a selection of one of said plurality of visual identifiers.

2. The method of claim 1, said generating step comprising:

identifying at least one phoneme associated with said selected visual identifier and inserting said identified at least one phoneme into said pronunciation information.

3. The method of claim 1, said generating step comprising:

identifying at least one phoneme associated with said selected visual identifier and removing said identified at least one phoneme from said pronunciation information.

4. The method of claim 1, wherein said pronunciation information comprises a plurality of phonemes, said generating step comprising:

reordering said plurality of phonemes of said pronunciation information.

5. The method of claim 1, wherein said pronunciation information comprises at least one parameter, said generating step comprising:

changing said at least one parameter of said pronunciation information.

6. The method of claim 5, wherein said parameter is selected from the group consisting of a stress parameter and a prosodic parameter.

7. The method of claim 1, further comprising:

playing an audio approximation of said pronunciation information responsive to a selection of one of said plurality of visual identifiers.

8. The method of claim 1, wherein said plurality of phonemes includes phonemes from at least two languages.

9. The method of claim 1, further comprising:

storing said pronunciation information in a memory.

10. A pronunciation composition tool comprising:

a library comprising a plurality of phonemes;

a graphical user interface comprising a plurality of activatable visual identifiers corresponding to particular ones of said plurality of phonemes; and

a processor configured to generate pronunciation information by including selected ones of said plurality of phonemes from said library responsive to a selection of at least one of said activatable visual identifiers.

11. The pronunciation tool of claim 10, further comprising:

a text-to-speech system configured to play an audio approximation of said pronunciation information responsive to activation of one of said activatable visual identifiers.

12. The pronunciation composition tool of claim 10, further comprising:

a compiler configured to compile said pronunciation information for use with a speech driven application.

13. The pronunciation composition tool of claim 10, wherein said processor is further configured to modify said pronunciation information.

14. The pronunciation tool of claim 10, wherein said plurality of phonemes comprise phonemes corresponding to at least two languages.

15. A machine-readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

graphically presenting at least one activatable visual identifier corresponding to individual ones of a plurality of phonemes;

responsive to a selection of one of said visual identifiers, generating said pronunciation information in accordance with said selected visual identifier; and

compiling said pronunciation information responsive to a selection of one of said plurality of visual identifiers.

16. The machine-readable storage of claim 15, said generating step comprising:

identifying at least one phoneme associated with said selected visual identifier and inserting said identified at least one phoneme into said pronunciation information.

17. The machine-readable storage of claim 15, said generating step comprising:

identifying at least one phoneme associated with said selected visual identifier and removing said identified at least one phoneme from said pronunciation information.

18. The machine-readable storage of claim 15, wherein said pronunciation information comprises a plurality of phonemes, said generating step comprising:

reordering said plurality of phonemes of said pronunciation information.

19. The machine-readable storage of claim 15, wherein said pronunciation information comprises at least one parameter, said modifying step comprising:

changing said at least one parameter of said pronunciation information.

20. The machine-readable storage of claim 19, wherein said parameter is selected from the group consisting of a stress parameter and a prosodic parameter.

21. The machine-readable storage of claim 15, further comprising:

playing an audio approximation of said pronunciation information responsive to a selection of one of said plurality of visual identifiers.

22. The machine-readable storage of claim 15, wherein said plurality of phonemes include phonemes from at least two languages.

23. The machine-readable storage of claim 15, further comprising:

storing said pronunciation information in a memory.