Method and apparatus for automatic creation of a voice recognition template entry

• US 5,671,328 A
• Filed: 12/30/1992
• Issued: 09/23/1997
• Est. Priority Date: 12/30/1992
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Fitzpatrick, Gregory P., Johnson, William J., Williams, Marvin L.
• Primary Examiner(s): Hafiz, Tariq R.
• Application Number:
  US07/998,286
• Time in Patent Office: 1,728 Days
• Field of Search: 395/2, 395/2.1-2.87, 381/36-53
• US Class Current: 704/246
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting

Abstract

A method and data processing system are disclosed for automatically creating voice processing template entries. In one embodiment, the invention automatically assembles a plurality of commands received by the data processing system, at least one of said commands having a voice recognition criteria component associated therewith, counts the occurrences of the plurality of commands, assembles voice recognition criteria components associated with the plurality of commands, and, as a result of the occurrence count exceeding a predefined minimum, constructs a voice recognition template entry by associating the assembled voice recognition criteria components with the assembled plurality of commands.

Claims

1. A method, performed in a data processing system, for the automatic creation of a voice recognition template entry, the method comprising the computer implemented steps of:

assembling a plurality of commands consecutively received by the data processing system into an assembled plurality of commands, at least one command of said assembled plurality of commands having a voice recognition criteria component associated therewith;

counting the occurrences of receipt, by the data processing system, of the assembled plurality of commands;

assembling the voice recognition criteria components associated with each command of said assembled plurality of commands into an assembled voice recognition criteria; and

as a result of the occurrence count exceeding a predefined minimum, constructing a voice recognition template entry by associating the assembled voice recognition criteria components with the assembled plurality of commands.

2. The method of claim 1, wherein the computer implemented step of assembling a plurality of commands consecutively received by the data processing system includes the computer implemented step of concatenating the plurality of commands consecutively received by the data processing system.

3. The method of claim 1, wherein the computer implemented step of assembling voice recognition criteria components associated with the assembled plurality of commands includes the computer implemented step of concatenating voice recognition criteria components associated with the assembled plurality of commands.

4. The method of claim 1, wherein the computer implemented step of assembling a plurality of commands consecutively received by the data processing system includes the computer implemented step of assembling a plurality of commands consecutively received by the data processing system beginning with a command having a start conglomeration attribute and ending with a command having an end conglomeration attribute.

5. The method of claim 1, further comprising the computer implemented step of associating a conglomeration attribute with the assembled plurality of commands.

6. A data processing system for the automatic creation of a voice recognition template entry, comprising:

means for assembling a plurality of commands consecutively received by the data processing system into an assembled plurality of commands, at least one command of said plurality of commands having a voice recognition criteria component associated therewith;

means for counting the occurrences of receipt, by the data processing system, of the assembled plurality of commands;

means for assembling the voice recognition criteria components associated with each command of said plurality of commands into an assembled voice recognition criteria; and

means for constructing, as a result of the occurrence count exceeding a predefined minimum, a voice recognition template entry by associating the assembled voice recognition criteria components with the assembled plurality of commands.

7. The data processing system of claim 6, wherein the means for assembling a plurality of commands consecutively received by the data processing system includes means for concatenating the plurality of commands consecutively received by the data processing system.

8. The data processing system of claim 6, wherein the means for assembling voice recognition criteria components associated with the assembled plurality of commands includes means for concatenating voice recognition criteria components associated with the assembled plurality of commands.

9. The data processing system of claim 6, wherein the means for assembling a plurality of commands consecutively received by the data processing system includes means for assembling a plurality of commands consecutively received by the data processing system beginning with a command having a start conglomeration attribute and ending with a command having an end conglomeration attribute.

10. The data processing system of claim 6, further comprising means for associating a conglomeration attribute with the assembled plurality of commands.