Machine assisted speech generation for a conversational voice response system

• US 7,647,227 B1
• Filed: 04/06/2004
• Issued: 01/12/2010
• Est. Priority Date: 04/06/2004
• Status: Active Grant

• Current Assignee: Intrado Interactive Services Corp.
• Original Assignee: TuVox, Inc. (West Corporation)
• Inventors: Khosla, Ashok Mitter
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US10/819,685
• Time in Patent Office: 2,107 Days
• Field of Search: 704/270.1
• US Class Current: 704/270.1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

In one embodiment, the invention provides a method for building a speech application. The method comprises reading data from a table; creating a data construct that models the structure of the table, in terms of fields contained therein; providing a user interface (UI) to display the structure of the table to a user; receiving a selection of data fields from the user; and automatically generating code for a voice browser (VB) based on the selection.

Claims

1. A method for building a speech application, the method comprising:

accessing a database;

reading data from a table in the database;

creating a data construct that models the structure of the table, in terms of fields contained therein;

displaying the structure of the table to a user;

receiving a selection of data fields from the user, the data fields to form the basis of navigation topics for voice browsing; and

automatically generating code for a voice browser (VB) based on the selection;

wherein the code enables the VB to guide a VB user by presenting the selection of fields to the VB user and allowing the VB user to utter a choice from the selection to be played.

2. The method of claim 1, further comprising reading a data source and automatically generating prompts therefrom for use in the generation of the code.

3. The method of claim 1, wherein the code is in a markup language.

4. The method of claim 1, further comprising reading a data source and automatically generating a grammar therefrom for use in the generation of the code.

5. A method for building a speech application, the method comprising:

accessing a database comprising a plurality of tables;

creating a data construct to represent each table and its structure in terms of data fields contained therein;

displaying the tables to a user for selection each table selected by the user to form the basis of navigation topics for voice browsing; and

receiving input from the user selecting tables that are to be presented as navigation topics by the VB; and

responsive to the input automatically generating code for a voice browser (VB) to guide a VB user by presenting navigation topics based on the tables to the VB user, and allowing the VB user to input an utterance selecting a navigation topic to be played by the VB.

6. The method of claim 5, further comprising providing a user interface (UI) to display the data construct to a user.

7. The method of claim 6, wherein automatically generating the code is based on the input from the user.

8. A computer readable medium, having stored there on a sequence of instructions which when executed by a computer, cause the computer to perform a method for building a speech application, the method comprising:

accessing a database;

reading data from a table in the database;

creating a data construct that models the structure of the table, in terms of fields contained therein;

displaying the structure of the table to a user;

receiving a selection of data fields from the user, the data field to form the basis of navigation topics for voice browsing; and

automatically generating code for a voice browser (VB) based on the selection;

wherein the code enables the VB to guide a VB user by presenting the selection of fields to the VB user and allowing the VB user to utter a choice from the selection to be played.

9. A system, comprising:

a processor; and

a memory coupled to the processor, the memory storing instructions which when executed by the processor cause the processor to perform a method for building a speech application, the method comprising;

accessing a database comprising a plurality of tables;

creating a data construct to represent each table and its structure in terms of data fields contained therein;

displaying the tables to a user for selection, each table selected by the user to form the basis of navigation topics for voice browsing; and

automatically generating code for a voice browser (VB) to guide a VB user by presenting navigation topics based on the tables to the VB user, and allowing the VB user to input an utterance selecting a navigation topic to be played by the VB.

10. The system of claim 9, further comprising providing a user interface (UI) to display the data construct to a user.

11. A system, comprising:

a processor; and

a memory coupled to the processor, the memory storing instructions which when executed by the processor, causes the system to perform a method for building a speech application, the method comprising;

accessing a database;

reading data from a table in the database;

creating a data construct that models the structure of the table, in terms of fields contained therein;

displaying the structure of the table to a user;

receiving a selection of data fields from the user, the data fields to form the basis of navigation topics to be used for voice navigation; and

automatically generating code for a voice browser (VB) based on the selection;

wherein the code enables the VB to guide a VB user by presenting the selection of fields to the VB user and allowing the VB user to utter a choice from the selection to be played.

12. A computer readable medium, having stored there on a sequence of instructions which when executed by a computer, cause the computer to perform a method for building a speech application, the method comprising:

accessing a database comprising a plurality of tables;

creating a data construct to represent each table and its structure in terms of data fields contained therein;

displaying the tables to a user for selection, each table selected by the user to form the basis of navigation topics for voice browsing; and

automatically generating code for a voice browser (VB) to guide a VB user by presenting navigation topics based on the tables selected by the user to the VB user, and allowing the VB user to input an utterance selecting a navigation topic to be played by the VB.

13. The computer readable medium of claim 12, further comprising providing a user interface (UI) to display the data construct to a user.