Enhanced accuracy for speech recognition grammars
View Patent ↗Disclosed herein are methods and systems for recognizing speech. A method embodiment comprises comparing received speech with a precompiled grammar based on a database and if the received speech matches data in the precompiled grammar then returning a result based on the matched data. If the received speech does not match data in the precompiled grammar, then dynamically compiling a new grammar based only on new data added to the database after the compiling of the precompiled grammar. The database may comprise a directory of names.
1. A method comprising:
comparing, via a processor, received speech with a precompiled grammar to yield a match result, wherein the precompiled grammar is based on a database; and
when the match result is below a threshold, comparing the received speech with a dynamically compiled grammar that is based only on new data added to the database after the precompiled grammar is compiled.
2. The method of claim 1 , wherein the dynamically compiled grammar is separate from the precompiled grammar.
3. The method of claim 1 , wherein the new data is obtained from one of: a table, a list, and an update database.
4. The method of claim 1 , wherein the database comprises a directory of names.
5. The method of claim 1 , further comprising dynamically compiling a new grammar when the received speech does not match data in the dynamically compiled grammar.
6. The method of claim 5 , wherein the new grammar comprises updated data from the database.
7. The method of claim 1 , wherein the received speech comprises an acoustic representation of a spoken name.
8. A system comprising:
a processor; and
a computer-readable medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
comparing received speech with a precompiled grammar to yield a match result, wherein the precompiled grammar is based on a database; and
when the match result is below a threshold, comparing the received speech with a dynamically compiled grammar that is based only on new data added to the database after the precompiled grammar is compiled.
9. The system of claim 8 , wherein the dynamically compiled grammar is separate from the precompiled grammar.
10. The system of claim 8 , wherein the database comprises a directory of names.
11. The system of claim 8 , wherein the new data is obtained from one of: a table, a list, and an update database.
12. The system of claim 8 , the computer-readable medium having additional instructions stored which result in the operations further comprising dynamically compiling a new grammar when the received speech does not match data in the dynamically compiled grammar.
13. The system of claim 12 , wherein the new grammar comprises updated data from the database.
14. A computer-readable medium having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
comparing received speech with a precompiled grammar to yield a match result, wherein the precompiled grammar is based on a database; and
when the match result is below a threshold, comparing the received speech with a dynamically compiled grammar that is based only on new data added to the database after the precompiled grammar is compiled.
15. The computer-readable medium of claim 14 , wherein the dynamically compiled grammar is separate from the precompiled grammar.
16. The computer-readable medium of claim 14 , wherein the database comprises a directory of names.
17. The computer-readable medium of claim 14 , wherein the new data is obtained from one of: a table, a list, and an update database.
18. The computer-readable medium of claim 14 , the computer-readable medium having additional instructions stored which, result in the operations further comprising dynamically compiling a new grammar when the received speech does not match data in the dynamically compiled grammar.
19. The computer-readable medium of claim 14 , wherein the new grammar comprises updated data from the database.
20. The computer-readable medium of claim 14 , wherein the received speech comprises an acoustic representation of a spoken name.