Multiple sound fragments processing and load balancing

• US 7,747,444 B2
• Filed: 03/03/2008
• Issued: 06/29/2010
• Est. Priority Date: 06/06/2002
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Moore, Victor S., McIntyre, Joseph Herbert
• Primary Examiner(s): Opsasnick; Michael N
• Application Number:
  US12/041,427
• Publication Number:
  US 20080147403A1
• Time in Patent Office: 848 Days
• Field of Search: 704/201, 704/270, 704500-504, 700/5, 700/7, 455/453, 711/118
• US Class Current: 704/270
• 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 computer readable storage medium encoded with computer executable instructions which, when executed by a processor, cause the processor to perform an operation, 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 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, determining, by the first processing system, whether the first set of sound fragments of the voice input matches with a set of sound fragments of a voice command; and

if the first set of sound fragments matches with the 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 computer readable storage medium of claim 1, wherein the number of sound fragments is determined by a load manager.

3. The computer readable storage medium of claim 1 ,wherein the number of sound fragments is reduced when the load of the first processing system exceeds a predefined threshold.

4. The computer readable storage medium of claim 1, wherein the operation further comprises 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 computer readable storage medium 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 computer readable storage medium of claim 1, wherein the operation further comprises 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 computer readable storage medium of claim 1, wherein the operation further comprises:

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 computer readable storage medium of claim 1, wherein the operation further comprises if the first set of sound fragments does not match with the set of sound fragments of the voice command, then discarding the voice input and processing a subsequent voice input.

9. The computer readable storage medium of claim 1, wherein the operation further comprises:

if the first set of sound fragments does not match with the 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 computer readable storage medium encoded with computer executable instructions which, when executed by a processor, cause the processor to perform an operation, 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, determining, by the first processing system, whether the first set of sound fragments of the voice input matches with a set of sound fragments of a voice command; and

if the first set of sound fragments matches with the 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 computer readable storage medium of claim 10, wherein the number of sound fragments depends on a load of the first processing system and a load of the second processing system.

12. The computer readable storage medium of claim 10, wherein determining, by the load manager, the number of sound fragments to be processed in the first set of sound fragments comprises:

monitoring a load of the first processing system and a load of the 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.

13. The computer readable storage medium of claim 10, wherein the operation further comprises 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.

14. A voice command recognition system, comprising:

a load manager configured for determining a number of sound fragments to be processed in a first set of sound fragments of a voice input wherein the number of sound fragments depends on a load of a first processing system and a load of a second processing system, and wherein the number of sound fragments is increased when the load of the second processing system exceeds a predefined threshold;

the first processing system comprising;

a memory containing a first voice command recognition program; and

a processor which, when executing the first voice command recognition program, performs an operation comprising;

receiving the voice input;

using the number of sound fragments, determining whether the 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 set of sound fragments of the voice command, then forwarding the voice input to the second processing system; and

the second processing system comprising;

a memory containing a second voice command recognition program; and

a processor which, when executing the second voice command recognition program, performs an operation comprising;

receiving the voice input from the first processing system; and

determining whether one or more remaining sound fragments matches with one or more remaining sound fragments of the voice command.

15. The system of claim 14, wherein the number of sound fragments is reduced when the load of the first processing system exceeds a predefined threshold.

16. The system of claim 14, wherein the operation of the second processing system further comprises:

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.

17. The system of claim 14, wherein determining whether one or more remaining sound fragments matches with 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 one or more remaining sound fragments from the total number of sound fragments in the voice command.

18. The system of claim 14, further comprising a database comprising a total number of sound fragments in each voice command;

and wherein determining whether one or more remaining sound fragments matches with one or more remaining sound fragments of the voice command comprises;

retrieving the total number of sound fragments from the database; and

determining the one or more remaining sound fragments from the total number of sound fragments in the voice command.