Speech recognition system for database access through the use of data domain overloading of grammars

A method for voice data entry availability in a voice response system comprising the steps of:

• receiving speech input in an audio user interface to a data information system for processing data in a data store, said speech input specifying data through an audio user interface to said data information system;
• performing speech-to-text conversion of said speech input using a speech recognition engine with reference to a corresponding speech recognition grammar;
• if said specified data is included in said speech recognition grammar, processing said speech data in said speech query if said specified data is in said data store, and indicating that said specified data was recognized but was not processed such that said data information system is unable to process said specified data if said specified data is not in said data store;
• and,
• if said specified data is not included in said speech grammar, reporting an Out-Of-Grammar (OOG) condition and not processing said speech data in said speech query,
• said speech recognition grammar containing a data set of words relating to said data information system;
• and,
• said data store containing a subset of said data set, said subset having words which can be processed by said data information system, said subset not having words which cannot be processed by said data information system, wherein said subset is derived from said speech recognition grammar.

A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine, said code sections for causing the machine to perform voice data entry availability in a voice response system, said code sections performing the steps of:

• receiving speech input in an audio user interface to a data information system for processing data in a data store, said speech input specifying data through an audio user interface to said data information system;
• performing speech-to-text conversion of said speech input using a speech recognition engine with reference to a corresponding speech recognition grammar;
• if said specified data is included in said speech recognition grammar, processing said speech data in said speech query if said specified data is in said data store, and indicating that said specified data was recognized but was not processed such that said data information system is unable to process said specified data if said specified data is not in said data store;
• and,
• if said specified data is not included in said speech grammar, reporting an Out-Of-Grammar (OOG) condition and not processing said speech data in said speech query,
• said speech recognition grammar containing a data set of words relating to said data information system;
• and,
• said data store containing a subset of said data set, said subset having words which can be processed by said data information system, said subset not having words which cannot be processed by said data information system, wherein said subset is derived from said speech recognition grammar.