Assisted speech recognition by dual search acceleration technique

• US 7,031,915 B2
• Filed: 01/23/2003
• Issued: 04/18/2006
• Est. Priority Date: 01/23/2003
• Status: Active Grant

• Current Assignee: Aurilab LLC
• Original Assignee: Aurilab LLC
• Inventors: Baker, James K.
• Primary Examiner(s): ARMSTRONG, ANGELA A
• Application Number:
  US10/348,966
• Publication Number:
  US 20040148164A1
• Time in Patent Office: 1,181 Days
• Field of Search: 704/231, 704/236, 704/239, 704/242, 704/251, 704/252, 704/255, 704/9
• US Class Current: 704/231
• CPC Class Codes: G10L 15/08 Speech classification or search

Abstract

A speech recognition method, system and program product, the method in one embodiment comprising: obtaining input speech data; initiating a first speech recognition search process with at least one hypothesis; initiating a second speech recognition search process with a plurality of hypotheses; obtaining partial results from the second speech recognition search process, where the partial results include an evaluation of at least one hypothesis that the first speech recognition search process has not evaluated at this point in time; and utilizing the partial results to alter the first speech recognition search process.

Claims

1. A speech recognition method, comprising:

obtaining input speech data;

initiating a first speech recognition search process with at least one hypothesis;

initiating a second speech recognition search process with a plurality of hypotheses;

obtaining partial results from the second speech recognition search process, where the partial results include an evaluation of at least one hypothesis that the first speech recognition search process has yet to evaluate at this point in time; and

utilizing the partial results to alter the first speech recognition search process,

wherein the first speech recognition search process proceeds from time frame to time frame at a different rate compared to the second speech recognition search process.

2. The method as defined in claim 1, wherein the first speech recognition search process is a priority queue process.

3. The method as defined in claim 1, wherein the first speech recognition search process is a priority queue process using a best first method.

4. The method as defined in claim 1, wherein the first and second speech recognition search processes are beam search processes.

5. The method as defined in claim 4, wherein the beam search process for the first speech recognition search process has a tighter pruning threshold than the beam search process for the second speech recognition search process.

6. A program product for speech recognition, comprising machine-readable program code for causing, when executed, a machine to perform the following method steps:

obtaining input speech data;

initiating a first speech recognition search process with at least one hypothesis;

initiating a second speech recognition search process with a plurality of hypotheses;

obtaining partial results from the second speech recognition search process, where the partial results include an evaluation of at least one hypothesis that the first speech recognition search process has yet to evaluate at this point in time; and

utilizing the partial results to alter the first speech recognition search process,

wherein the first speech recognition search process proceeds from time frame to time frame at a different rate compared to the second speech recognition search process.

7. The program product as defined in claim 6, wherein the first speech recognition search process is a priority queue process.

8. The program product as defined in claim 6, wherein the first speech recognition search process is a priority queue process using a best first method.

9. The program product as defined in claim 6, wherein the first and second speech recognition search processes are beam search processes.

10. The program product as defined in claim 9, wherein the beam search process for the first speech recognition search process has a tighter pruning threshold than the beam search process for the second speech recognition search process.

11. A speech recognition method, comprising:

obtaining input speech data;

initiating a first speech recognition search process using a first parameter and a pruning threshold substantially simultaneously on a first plurality of hypotheses;

initiating a second speech recognition search process substantially simultaneously on a second plurality of hypotheses wherein a second parameter for the second speech recognition search process is different from the first parameter for the first speech recognition search process;

obtaining partial results at a point in time from the second speech recognition search process, where the partial results include an evaluation of at least one hypothesis that the priority queue search process has yet to evaluate at that point in time and a score for that hypothesis;

determining if the score for the at least one hypothesis evaluated by the second speech recognition search process for a particular time frame is better than a best score for that time frame for any hypothesis evaluated by the first speech recognition search process by more than a predetermined amount; and

if yes, then restarting the first speech recognition search process at that point in time on a plurality of hypotheses that include the at least one hypothesis that the first speech recognition search process has yet to evaluate and using a new pruning threshold,

wherein a second parameter is a number of hypotheses being evaluated by the second speech recognition search process, which is larger than the number of hypotheses being evaluated the first speech recognition search process.

12. A speech recognition system, comprising:

a component for obtaining input speech data;

a component for initiating a first speech recognition search process using a first parameter and a pruning threshold substantially simultaneously on a first plurality of hypotheses;

a component for initiating a second speech recognition search process substantially simultaneously on a second plurality of hypotheses wherein a parameter for the second speech recognition search process is different from the first parameter for the first speech recognition search process;

a component for obtaining partial results at a point in time from the second speech recognition search process, where the partial results include an evaluation of at least one hypothesis that the first speech recognition search process has yet to evaluate at that point in time and a score for that hypothesis;

a component for determining if the score for the at least one hypothesis evaluated by the second speech recognition search process for a particular time frame is better than a best score for that time frame for any hypothesis evaluated by the first speech recognition search process by more than a predetermined amount; and

a component for, if yes, then restarting the first speech recognition search process at that point in time on a plurality of hypotheses that include the at least one hypothesis that the first speech recognition search process has yet to evaluate and using a new pruning threshold,

wherein a second parameter is a number of hypotheses being evaluated by the second speech recognition search process, which is larger than the number of hypotheses being evaluated by the first speech recognition search process.

13. A program product for speech recognition, comprising machine-readable program code for causing, when executed, a machine to perform the following method steps:

obtaining input speech data;

initiating a first speech recognition search process using a first parameter and a pruning threshold substantially simultaneously on a first plurality of hypotheses;

initiating a second speech recognition search process substantially simultaneously on a second plurality of hypotheses wherein a second parameter for the second speech recognition search process is different from the first parameter for the first speech recognition search process;

obtaining partial results at a point in time from the second speech recognition search process, where the partial results include an evaluation of at least one hypothesis that the first speech recognition search process has yet to evaluate at that point in time and a score for that hypothesis;

determining if the score for the at least one hypothesis evaluated by the second speech recognition search process for a particular time frame is better than a best score for that time frame for any hypothesis evaluated by the first speech recognition search process by more than a predetermined amount; and

if yes, then restarting the first speech recognition search process at that point in time on a plurality of hypotheses that include the at least one hypothesis that the first speech recognition search process has yet to evaluate and using a new pruning threshold,

wherein a second parameter is a number of hypotheses being evaluated by the second speech recognition search process, which is larger than the number of hypotheses being evaluated by the first speech recognition search process.