CROWD-SOURCING PRONUNCIATION CORRECTIONS IN TEXT-TO-SPEECH ENGINES

• US 20130179170A1
• Filed: 01/09/2012
• Published: 07/11/2013
• Est. Priority Date: 01/09/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Cath, Jeremy Edward, Harris, Timothy Edwin, Tisdale, James Oliver III
• Granted Patent: US 9,275,633 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

Technologies are described herein for providing validated text-to-speech correction hints from aggregated pronunciation corrections received from text-to-speech applications. A number of pronunciation corrections are received by a Web service. The pronunciation corrections may be provided by users of text-to-speech applications executing on a variety of user computer systems. Each of the plurality of pronunciation corrections includes a specification of a word or phrase and a suggested pronunciation provided by the user. The pronunciation corrections are analyzed to generate validated correction hints, and the validated correction hints are provided back to the text-to-speech applications to be used to correct pronunciation of words and phrases in the text-to-speech applications.

Claims

1. A system for providing validated text-to-speech correction hints to text-to-speech applications, the system comprising:

one or more application servers;

a correction submission service executing on the one or more application servers and comprising computer-executable instructions that cause the system to

receive a plurality of pronunciation corrections comprising a specification of a word or phrase and a suggested pronunciation, each of the plurality of pronunciation corrections provided by a user of a text-to-speech application executing on a user computer system, and

store the plurality of pronunciation corrections in a data storage system; and

a correction validation module executing on the one or more application servers and comprising computer-executable instructions that cause the system to

analyze the plurality of pronunciation corrections and generate a validated correction hint when a threshold number of pronunciation corrections are received for the word or phrase having substantially the same suggested pronunciation, and

provide the validated correction hint back to the text-to-speech applications, wherein the validated correction hint is utilized to correct a pronunciation of the word or phrase in the text-to-speech applications.

2. The system of claim 1, wherein each of the plurality of pronunciation corrections further comprises a specification of a locale of usage, and wherein a validated correction hint is generated for the locale when a threshold number of pronunciation corrections are received for the word or phrase having substantially the same suggested pronunciation and the same locale of usage.

3. The system of claim 1, wherein each of the plurality of pronunciation corrections further comprises a specification of a class of submitter, and wherein a validated correction hint is generated for the class when a threshold number of pronunciation corrections are received for the word or phrase having substantially the same suggested pronunciation and the same class of submitter.

4. The system of claim 1, wherein each of the plurality of pronunciation corrections further comprises a specification of a submitter, and wherein submitter ratings regarding the submitter are utilized in generating the validated correction hints.

5. The system of claim 1, wherein the correction submission service comprises a Web service.

6. A computer-implemented method for providing validated text-to-speech correction hints to text-to-speech applications, the method comprising:

receiving a plurality of pronunciation corrections;

analyzing the plurality of pronunciation corrections to generate one or more validated correction hints; and

providing the validated correction hints to text-to-speech applications, wherein the validated correction hints are utilized to correct a pronunciation of words and phrases in the text-to-speech applications.

7. The computer-implemented method of claim 6, wherein the plurality of pronunciation corrections are received from user computer systems, each of the plurality of pronunciation corrections provided by a user of a text-to-speech application executing on the user computer system.

8. The computer-implemented method of claim 7, wherein each of the plurality of pronunciation corrections comprises a specification of a word or phrase and a suggested pronunciation provided by the user.

9. The computer-implemented method of claim 8, wherein a validated correction hint is generated when a confidence level for a suggested pronunciation is determined from a number of pronunciation corrections received for a same word or phrase.

10. The computer-implemented method of claim 8, wherein each of the plurality of pronunciation corrections further comprises a specification of a locale of usage, and wherein a validated correction hint is generated for the locale when a confidence level for a suggested pronunciation is determined from a number of pronunciation corrections received for a same word or phrase having a same locale of usage.

11. The computer-implemented method of claim 8, wherein each of the plurality of pronunciation corrections further comprises a specification of a class of submitter, and wherein a validated correction hint is generated for the class when a confidence level for a suggested pronunciation is determined from a number of pronunciation corrections received for a same word or phrase having a same class of submitter.

12. The computer-implemented method of claim 8, wherein each of the plurality of pronunciation corrections further comprises a specification of a submitter, and wherein submitter ratings regarding the submitter are utilized in determining the confidence level of the suggested pronunciation.

13. The computer-implemented method of claim 8, wherein the suggested pronunciation comprises a phonetic spelling of the word or phrase selected by the user from a list of alternate phonetic spellings for the word or phrase.

14. The computer-implemented method of claim 8, wherein the suggested pronunciation comprises a recording of the user speaking the word or phrase.

15. The computer-implemented method of claim 6, wherein a text-to-speech application utilizes the validated correction hints to update a local pronunciation dictionary utilized by the text-to-speech application.

16. The computer-implemented method of claim 6, wherein the plurality of pronunciation corrections are received from the text-to-speech applications through a Web service.

17. A computer-readable storage medium encoded with computer-executable instructions that, when executed by a computer, cause the computer to:

receive a plurality of pronunciation corrections provided by users of text-to-speech applications executing on a plurality of user computer systems, each of the plurality of pronunciation corrections comprising a specification of a word or phrase and a suggested pronunciation provided by the user;

store the pronunciation corrections in a data storage system;

analyze the plurality of pronunciation corrections to generate one or more validated correction hints; and

provide the validated correction hints back to the text-to-speech applications, wherein the validated correction hints are utilized to correct pronunciation of words and phrases in the text-to-speech applications.

18. The computer-readable storage medium of claim 17, wherein a validated correction hint is generated when a confidence level for a suggested pronunciation is determined from a number of pronunciation corrections received for a same word or phrase.

19. The computer-readable storage medium of claim 17, wherein each of the plurality of pronunciation corrections further comprises a specification of a locale of usage, and wherein a validated correction hint is generated for the locale when a confidence level for a suggested pronunciation is determined from a number of pronunciation corrections received for a same word or phrase having a same locale of usage.

20. The computer-readable storage medium of claim 19, wherein the validated correction hint for the locale is utilized to correct pronunciation of the word or phrase by the text-to-speech applications executing on user computer systems in the locale.