Enhanced accuracy for speech recognition grammars
AssigneeAT&T Intellectual Property II, L.P.
InventorsHarry Blanchard, Steven Lewis, Shankarnarayan Sivaprasad, Lan Zhang
Life of this patent
Estimating the term…
Abstract
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.
Claims12
A method of recognizing speech, the method causing a computing device to perform steps comprising:
- comparing via a processor received speech with a precompiled grammar based on a database;
- if the received speech matches data in the precompiled grammar, then returning a result based on matched data;
- and
- 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 new grammar being separate from the precompiled grammar.
A computing device for recognizing speech, the computing device comprising:
- a first module controlling a processor to compare received speech with a precompiled grammar based on a database;
- a second module controlling the processor to return a result based on matched data if the received speech matches data in the precompiled grammar;
- and
- a third module controlling the processor to dynamically compile a new grammar based only on new data added to the database after the compiling of the precompiled grammar if the received speech does not match data in the precompiled grammar, the new grammar being separate from the precompiled grammar.
A computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to recognize speech, the instructions comprising:
- comparing received speech with a precompiled grammar based on a database;
- if the received speech matches data in the precompiled grammar, then returning a result based on matched data;
- and
- 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 new grammar being separate from the precompiled grammar.
Dependencies are inferred from the claim text.