Automatic speech recognition tagging

• US 9,093,073 B1
• Filed: 02/12/2007
• Issued: 07/28/2015
• Est. Priority Date: 02/12/2007
• Status: Active Grant

• Current Assignee: West Technology Group LLC (West Corporation)
• Original Assignee: West Corporation
• Inventors: Fisher, Aaron Scott, Pradhan, Prashanta
• Primary Examiner(s): Pullias, Jesse
• Application Number:
  US11/673,665
• Time in Patent Office: 3,088 Days
• Field of Search: 704/257, 704E15018- 9, 704/24, 704/26
• US Class Current: 1/1
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method, a computer readable medium and a system for tagging automatic speech recognition that comprises, collecting an utterance, analyzing the utterance, and assigning a tag to the analyzed utterance.

Claims

1. A computer implemented method, comprising:

collecting an utterance;

analyzing the utterance;

creating a tagging strategy;

providing the tagging strategy to a tagging server;

predicting a potential tag for the utterance;

assigning a tag to the analyzed utterance;

assigning a context category to the tagged utterance; and

combining identical tag assignments,

wherein the utterance is compressed and expanded by a tagging server.

2. The computer implemented method of claim 1, further comprising:

determining a semantic meaning of the utterance.

3. The computer implemented method of claim 2, further comprising:

grouping utterances that share semantic meanings.

4. The computer implemented method of claim 1, further comprising:

storing the utterance.

5. The computer implemented method of claim 1, further comprising:

transcribing the utterance.

6. The computer implemented method of claim 1, further comprising:

building a semantic interpretation grammar based on the tagged utterance.

7. The computer implemented method of claim 1, further comprising:

correlating tagged utterances according to a semantic meaning.

8. The computer implemented method of claim 1, wherein the analysis of the utterance occurs in parallel to the assignment of the tag.

9. A non-transitory computer readable medium comprising instructions that, when executed by a processor, are configured to cause the processor to:

record an utterance;

transcribe the utterance;

evaluate the transcribed utterance;

create a tagging strategy;

provide the tagging strategy to a tagging server;

predict a potential tag of the evaluated utterance;

assign a tag to the evaluated utterance;

assign a context category to the tagged utterance; and

combine identical tag assignments,

wherein the utterance is compressed and expanded by a tagging server.

10. The computer readable medium of claim 9, wherein the instructions are further configured to cause the processor to:

create a semantic interpretation grammar based upon the tagged utterance.

11. The computer readable medium of claim 9, wherein the instructions are further configured to cause the processor to:

collect differences between the predicted potential tag and the assigned tag.

12. The computer readable medium of claim 9, wherein the instructions are further configured to cause the processor to:

group similar context categories.

13. The computer readable medium of claim 9, wherein the instructions are further configured to cause the processor to:

group similar tagged utterances.

14. A system, comprising:

a memory; and

a processor communicably coupled to the memory, wherein the processor is configured to;

receive an utterance;

transcribe the received utterance;

analyze the transcribed utterance;

create a tagging strategy;

provide the tagging strategy to a tagging server;

predict a potential tag of the utterance;

tag the transcribed utterance;

group similarly analyzed utterances;

combine identical tag assignments;

categorize the similarly analyzed utterances by similar contexts; and

discard replicate groupings of similarly analyzed utterances;

wherein the utterance is compressed and expanded by a tagging server.

15. The system of claim 14, wherein the processor is further configured to:

coordinate access to the utterance.