System and method for speech trend analytics with objective function and feature constraints

• US 9,213,978 B2
• Filed: 09/30/2010
• Issued: 12/15/2015
• Est. Priority Date: 09/30/2010
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Melamed, Ilya Dan, Gilbert, Mazin
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US12/895,337
• Publication Number:
  US 20120084081A1
• Time in Patent Office: 1,902 Days
• Field of Search: 704/231, 704/235, 704/236, 704/251, 704/270, 379/265.06, 379/266.1, 706/12, 706/13, 706/19
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/01 Customer relationship services

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing trend analysis of speech. A system practicing the method receives a speech trend analysis request having candidate feature constraints, an objective function with respect to a speech trend to be analyzed, and a set of speech record constraints. The system selects a subset of speech records from the group of speech records based on the set of speech record constraints to yield selected speech records, identifies features in the selected speech records based on the set of candidate feature constraints to yield identified features, and assigns a weight to each of the identified features based on the objective function. Then the system ranks the identified features by their respective weights to yield ranked identified features, and outputs at least one of the ranked identified features associated with a speech-based trend in response to the speech trend analysis request.

Claims

1. A method comprising:

receiving, as part of a speech trend analysis request, a set of candidate feature constraints, an objective mathematical function with respect to a speech trend to be analyzed, and a set of speech record constraints to be applied to a group of speech records;

selecting a speech record from the group of speech records based on the set of speech record constraints;

identifying features in the speech record based on the set of candidate feature constraints, to yield identified features;

assigning, via a processor, using a statistical regression, a weight to each of the identified features, wherein a scalar value associated with each identified feature is evaluated using the objective mathematical function to yield the weight;

ranking the identified features by respective weights, to yield ranked identified features;

comparing the ranked identified features to a hand-picked set of alarm features, to yield a comparison; and

when the comparison indicates an alarm condition has been met, outputting one of the ranked identified features associated with a speech-based trend in response to the speech as an alarm.

2. The method of claim 1, wherein the group of speech records comprises one of recorded speech, transcriptions, and metadata.

3. The method of claim 1, wherein selecting the speech record from the group of speech records further comprises:

generating a database query command corresponding to the speech record constraints; and

executing the database query command.

4. The method of claim 3, wherein results of executing the database query command are passed to a feature filtering module which identifies the features in the selected speech records, and wherein the results of executing the database query are not output to a user via a display device.

5. The method of claim 1, wherein the set of candidate feature constraints constrains one of transcript features, metadata features, and higher order features inferred from the transcript features and metadata features.

6. The method of claim 1, wherein the objective mathematical function utilizes a combination of features and time.

7. The method of claim 1, wherein the ranked identified features output via a user interface in which a user can focus on records with highly predictive features.

8. The method of claim 1, wherein, after outputting the ranked identified features, a user can revise the speech trend analysis request.

9. The method of claim 8, wherein revising the speech trend analysis request further comprises filtering out an undesired feature constraint from the set of candidate feature constraints.

10. A non-transitory computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:

receiving, as part of a speech trend analysis request, a set of candidate feature constraints, an objective mathematical function with respect to a speech trend to be analyzed, and a set of speech record constraints to be applied to a group of speech records;

selecting a subset of speech records from the group of speech records based on the set of speech record constraints to yield selected speech records;

identifying features in the selected speech records based on the set of candidate feature constraints to yield identified features;

assigning, via a processor, using a statistical regression, a weight to each of the identified features, wherein a scalar value associated with each identified feature is evaluated using the objective mathematical function to yield the weight;

ranking the identified features by respective weights to yield ranked identified features;

comparing the ranked identified features to a hand-picked set of alarm features, to yield a comparison; and

when the comparison indicates an alarm condition has been met, outputting one of the ranked identified features associated with a speech-based trend in response to the speech as an alarm.

11. The non-transitory computer-readable storage device of claim 10, wherein, after outputting one of the ranked identified features, a user can revise the speech trend analysis request.

12. A system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising;

receiving, as part of a speech trend analysis request, a set of candidate feature constraints selected by an analyst, an objective mathematical function with respect to a speech trend to be analyzed, and a set of speech record constraints to be applied to a group of speech records;

selecting a speech record from the group of speech records based on the set of speech record constraints;

identifying features in the speech record based on the set of candidate feature constraints, to yield identified features;

assigning, via a processor, using a statistical regression, a weight to each of the identified features, wherein a scalar value associated with each identified feature is evaluated using the objective mathematical function to yield the weight;

ranking the identified features by respective weights, to yield ranked identified features;

comparing the ranked identified features to a hand-picked set of alarm features, to yield a comparison; and

when the comparison indicates an alarm condition has been met, outputting one of the ranked identified features associated with a speech-based trend in response to the speech as an alarm.

13. The system of claim 12, wherein the group of speech records comprises one of recorded speech, transcriptions, and metadata.

14. The system of claim 12, wherein selecting the speech record from the group of speech records further comprises:

generating a database query command corresponding to the speech record constraints; and

executing the database query command.

15. The system of claim 14, wherein results of executing the database query command are passed to a feature filtering module which identifies the features in the selected speech records, and wherein the results of executing the database query are not output to a user via a display device.

16. The system of claim 12, wherein the set of candidate feature constraints constrains one of transcript features, metadata features, and higher order features inferred from the transcript features and metadata features.

17. The system of claim 12, wherein the objective mathematical function utilizes a combination of features and time.

18. The system of claim 12, wherein the ranked identified features output via a user interface in which a user can focus on records with highly predictive features.

19. The system of claim 12, wherein, after outputting the ranked identified features, a user can revise the speech trend analysis request.