Creating a speech recognition grammar for alphanumeric concepts

• US 20060069547A1
• Filed: 09/15/2004
• Published: 03/30/2006
• Est. Priority Date: 09/15/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ju, Yun-Cheng, Acero, Alejandro, Wang, Ye-Yi, Collins, Leonard Alan, Cecys, Mark
• Granted Patent: US 7,599,837 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks

Abstract

A method and system to generate a grammar adapted for use by a speech recognizer includes receiving a representation of an alphanumeric expression. For instance, the representation can take the form of a regular expression or a mask. The grammar is generated based on the representation.

Claims

1. A computer implemented method to generate a grammar adapted for use by a speech recognizer, the method comprising:

receiving a representation of an alphanumeric expression; and

generating a grammar based on the representation.

2. The computer implemented method of claim 1 wherein generating the grammar comprises parsing the representation into portions.

3. The computer implemented method of claim 2 wherein generating the grammar includes generating grammar rules for each of the portions.

4. The computer implemented method of claim 3 wherein parsing the representation includes parsing the representation into branches.

5. The computer implemented method of claim 4 wherein generating the grammar includes generating grammar rules for each of the branches.

6. The computer implemented method of claim 3 wherein generating the grammar includes identifying smaller portions of each of the first-mentioned portions of the representation and generating the grammar includes generating rules for each of the smaller portions.

7. The computer implemented method of claim 6 wherein generating grammar rules for each of the smaller portions includes identifying a smaller portion having rules stored in a library and generating rules for the grammar based on the rules stored in the library.

8. The computer implemented method of claim 6 wherein generating grammar rules for each of the smaller portions includes generating rules for alternative character spoken expressions.

9. The computer implemented method of claim 8 wherein generating the grammar includes using a mechanism to provide a normalized output from a speech recognizer for recognition of alternative character spoken expressions.

10. The computer implemented method of claim 9 wherein generating the grammar includes providing normalization information in the grammar so as to provide a normalized output from a speech recognizer for recognition of alternative character spoken expressions.

11. The computer implemented method of claim 10 wherein generating the grammar includes generating a database associated with the grammar, the database having normalization information.

12. The computer implemented method of claim 6 wherein generating grammar rules for each of the smaller portions includes generating rules for alternative character sequence spoken expressions.

13. The computer implemented method of claim 9 wherein generating the grammar includes using a mechanism to provide a normalized output from a speech recognizer for recognition of alternative character spoken expressions.

14. The computer implemented method of claim 13 wherein generating the grammar includes providing normalization information in the grammar so as to provide a normalized output from a speech recognizer for recognition of alternative character spoken expressions.

15. The computer implemented method of claim 14 wherein generating the grammar includes generating a database associated with the grammar, the database having normalization information.

16. The computer implemented method of claim 6 wherein generating grammar rules for each of the smaller portions includes identifying a first smaller portion that is identical to a second smaller portion in the representation that grammar rules have previously been based on and generating rules based on the first smaller portion by using the rules based on the second smaller portion.

17. The computer implemented method of claim 1 wherein generating the grammar includes generating prefix optimized grammar rules.

18. The computer implemented method claim 1 wherein the representation is of the form of a regular expression or a mask.

19. A computer readable medium having instructions operable on a computer to generate a grammar adapted for use by a speech recognizer, the instructions comprising:

receiving a representation of an alphanumeric expression; and

generating a grammar based on the representation.

20. The computer readable medium of claim 19 wherein the representation comprises a regular expression or a mask.

21. The computer readable medium of claim 20 wherein generating a grammar includes identifying branches and pieces of the representation.

22. The computer readable medium of claim 21 wherein generating the grammar includes generating rules for each of the branches and each of the pieces.

23. The computer readable medium of claim 22 wherein generating rules for each of the pieces includes at least one of generating rules for alternative character spoken expressions;

generating rules for alternative character sequence spoken expressions; and

identifying a piece having rules stored in a library and generating rules for the grammar based on the rules stored in the library.

24. The computer readable medium of claim 23 wherein generating the grammar includes using a mechanism to provide a normalized output from a speech recognizer for recognition of at least one of alternative character spoken expressions and alternative character sequence spoken expressions.

25. The computer readable medium of claim 24 wherein generating the grammar includes providing normalization information in the grammar so as to provide a normalized output from a speech recognizer for recognition of at least one of alternative character spoken expressions and alternative character sequence spoken expressions.

26. The computer readable medium of claim 25 wherein generating the grammar includes generating a database associated with the grammar, the database having normalization information for at least one of alternative character spoken expressions and alternative character sequence spoken expressions.

30. The system of claim 26 wherein the piece rule generator is adapted to generate rules for at least one of alternative character spoken expressions and alternative character sequence spoken expressions.

31. The system of claim 30 wherein the piece rule generator is adapted to provide normalization information in the grammar for at least one of alternative character spoken expressions and alternative character sequence spoken expressions.

27. A computer system to generate a grammar adapted for use by a speech recognizer, the computer system comprising:

a parsing module adapted to receiving a representation of an alphanumeric expression and identify branches of the representation;

a branch rule generator module adapted to generate rules for the grammar based on the branches; and

a piece rule generator module adapted to identify pieces of each of the branches and generate rules for the grammar based on each of the pieces.

28. The system of claim 27 and further comprising a library for storing grammar rules based on pieces and wherein the piece rule generator is adapted to identify a piece of the representation corresponding to a piece having rules stored in the library, and wherein the piece rule generator is adapted to generate rules for the grammar based on the rules in the library.

29. The system of claim 28 wherein the piece rule generator is adapted to store rules in the library for a first piece of the representation that has been processed, and wherein the piece rule generator is adapted to identify a second piece of the representation that is identical to the first piece of the representation and generate rules for the second piece of the representation based on the rules in the library for the first piece of the representation.