Multiple sound fragments processing and load balancing

• US 7,340,392 B2
• Filed: 06/06/2002
• Issued: 03/04/2008
• Est. Priority Date: 06/06/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Moore, Victor S., McIntyre, Joseph Herbert
• Primary Examiner(s): Opsasnick; Michael N
• Application Number:
  US10/164,972
• Publication Number:
  US 20030229493A1
• Time in Patent Office: 2,098 Days
• Field of Search: 704/201, 704/270, 704500-504, 700/5, 700/7, 455/453, 711/118
• US Class Current: 704/201
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method, system and article of manufacture of recognizing a voice command. One embodiment of the invention comprises: receiving a voice input; using the number of sound fragments, determining a number of sound fragments to be processed in a first set of sound fragments; determining whether the first set of sound fragments of the voice input matches with the first set of sound fragments of a voice command; and if the first set of sound fragments matches with the first set of sound fragments of the voice command, then determining whether one or more remaining sound fragments matches with one or more remaining sound fragments of the voice command.

Claims

1. A method of recognizing a voice command, comprising:

receiving a voice input;

determining a number of sound fragments to be processed in a first set of sound fragments of the voice input by;

monitoring a load of a first processing system and a load of a second processing system; and

determining the number of sound fragments of the voice input based on the load of the first processing system and the load of the second processing system, wherein the number of sound fragments of the voice input is increased when the load of the second processing system exceeds a predefined threshold;

using the number of sound fragments, determining, by the first processing system, whether the first set of sound fragments from the voice input matches with a first set of sound fragments of a voice command; and

if the first set of sound fragments matches with the first set of sound fragments of the voice command, then determining, by the second processing system, whether one or more remaining sound fragments matches with one or more remaining sound fragments of the voice command.

2. The method of claim 1, wherein the number of sound fragments of the voice input is determined by a load manager.

3. The method of claim 1,

wherein the number of sound fragments of the voice input is reduced when the load of the first processing system exceeds a predefined threshold.

4. The method of claim 1, further comprising if the one or more remaining sound fragments matches with the one or more remaining sound fragments of the voice command, then invoking an action for which the voice command is configured.

5. The method of claim 1, wherein determining whether the one or more remaining sound fragments matches with the one or more remaining sound fragments of the voice command comprises:

retrieving a total number of sound fragments in the voice command; and

determining the remaining sound fragments from the total number of sound fragments.

6. The method of claim 1, further comprising if the one or more remaining sound fragments does not match with the one or more remaining sound fragments of the voice command, then discarding the voice input.

7. The method of claim 1, further comprising:

if the one or more remaining sound fragments matches with the one or more remaining sound fragments of the voice command, then invoking an action for which the voice command is configured; and

if the one or more remaining sound fragments do not match with the one or more remaining sound fragments of the voice command, then discarding the voice input.

8. The method of claim 1, further comprising if the first set of sound fragments does not match with the first set of sound fragments of the voice command, then discarding the voice input and processing a subsequent voice input.

9. The method of claim 1, further comprising:

if the first set of sound fragments does not match with the first set of sound fragments of the voice command, then discarding the voice input and processing a subsequent voice input;

if the one or more remaining sound fragments matches with the one or more remaining sound fragments of the voice command, then invoking an action for which the voice command is configured; and

if the one or more remaining sound fragments do not match with the one or more remaining sound fragments of the voice command, then discarding the voice input.

10. A method of recognizing a voice command, comprising:

receiving a voice input;

determining, by a load manager, a number of sound fragments to be processed in a first set of sound fragments of the voice input by;

monitoring a load of a first processing system and a load of a second processing system, and

determining the number of sound fragments based on the load of the first processing system and the load of the second processing system, wherein the number of sound fragments is increased when the load of the second processing system exceeds a predefined threshold;

using the number of sound fragments of the voice input, determining, by the first processing system, whether the first set of sound fragments of the voice input matches with a first set of sound fragments of a voice command; and

if the first set of sound fragments matches with the first set of sound fragments of the voice command, then determining, by the second processing system, whether one or more remaining sound fragments matches with one or more remaining sound fragments of the voice command.

11. The method of claim 10, further comprising if the one or more remaining sound fragments matches with the one or more remaining sound fragments of the voice command, then invoking an action for which the voice command is configured.