System and method for dynamic ASR based on social media

• US 9,646,604 B2
• Filed: 09/15/2012
• Issued: 05/09/2017
• Est. Priority Date: 09/15/2012
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Avaya Incorporated
• Inventors: Erhart, George W., Matula, Valentine C., Skiba, David J.
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): Nguyen, Timothy
• Application Number:
  US13/621,086
• Publication Number:
  US 20140081636A1
• Time in Patent Office: 1,697 Days
• Field of Search: 704236
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06Q 30/0281 Customer communication at a business location, e.g. providing product or service information, consulting
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/40 related to call centers
• CPC Class Codes: H04M 2203/655 Combination of telephone service and social networking messaging within social networks H04L51/52
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5191 interacting with the Internet

Abstract

System and method to adjust an automatic speech recognition (ASR) engine, the method including: receiving social network information from a social network; data mining the social network information to extract one or more characteristics; inferring a trend from the extracted one or more characteristics; and adjusting the ASR engine based upon the inferred trend. Embodiments of the method may further include: receiving a speech signal from a user; and recognizing the speech signal by use of the adjusted ASR engine. Further embodiments of the method may further include: producing a list of candidate matching words; and ranking the list of candidate matching words by use of the inferred trend.

Claims

1. A method to adjust an automatic speech recognition (ASR) engine, comprising:

receiving, by a social media gateway of a contact center, social network information from a social network;

modifying, by the social media gateway of the contact center, the social network information, wherein the modifying comprises filtering the social network information and redacting the filtered social network information based on a relevancy of the social network information to the ASR engine;

data mining, by a dialog engine of the contact center, the modified social network information to extract one or more characteristics;

inferring, by the dialog engine of the contact center, a trend from the extracted one or more characteristics;

adding, by the dialog engine of the contact center, one or more words or phrases related to the trend to a recognition grammar of the ASR engine;

calculating, by the dialog engine of the contact center, a magnitude of adjustment to weights of the added one or more words or phrases in the recognition grammar of the ASR engine based upon a shaped sliding window, and

adjusting, by the dialog engine of the contact center, the ASR engine by adjusting a speech recognition weighting of the ASR engine based upon the calculated magnitude of adjustment, wherein the adjustment to the speech recognition weighting of the ASR engine has a limited duration.

2. The method of claim 1, further comprising:

receiving a speech signal from a user; and

recognizing the speech signal by use of the adjusted ASR engine.

3. The method of claim 2, wherein recognizing the speech signal further comprises:

producing a list of candidate matching words; and

ranking the list of candidate matching words.

4. The method of claim 1, wherein adjusting the ASR engine comprises changing a routing path.

5. The method of claim 1, wherein adjusting the ASR engine comprises modifying a lexicon used by the ASR engine.

6. The method of claim 1, wherein adjusting the ASR engine comprises adjusting the recognition grammar used by the ASR engine.

7. The method of claim 1, wherein the ASR engine is adjusted in response to a specificity of the one or more characteristics.

8. The method of claim 1, further comprising:

estimating a persistence of the trend; and

limiting the duration of the adjustment to the ASR engine based upon the estimated persistence.

9. The method of claim 1, wherein the step of data mining is performed within a domain of interest of the ASR engine.

10. A system of a contact center to adjust an automatic speech recognition (ASR) engine, comprising:

a first processor;

a first storage device in communication with the first processor, storing first executable instructions, wherein the executable instructions, when executed by the processor, cause the processor to;

receive social network information from a social network; and

modify the social network information, wherein the modifying comprises filtering the social network information and redacting the filtered social network information based on a relevancy of the social network information to the ASR engine;

a second processor, in communication with the first processor; and

a second storage device in communication with the second processor, wherein the second executable instructions, when executed by the second processor, cause the second processor to;

data mine the modified social network information to extract one or more characteristics;

infer a trend from the extracted one or more characteristics;

add one or more words or phrases related to the trend to a recognition grammar of the ASR engine;

calculate a magnitude of an adjustment to weights of the added one or more words or phrases in the recognition grammar of the ASR engine based upon a shaped sliding window; and

adjust the ASR engine by adjusting a speech recognition weighting of the ASR engine based upon the calculated magnitude of adjustment, wherein the adjustment to the speech recognition weighting of the ASR engine has a limited duration.

11. The system of claim 10, wherein the second executable instructions, when executed by the second processor, cause the second processor to:

receive a speech signal from a user, wherein the speech signal is recognized by use of the adjusted ASR engine.

12. The system of claim 10, wherein the second executable instructions, when executed by the second processor, cause the second processor to:

estimate a persistence of the trend and to limit a duration of the adjustment to the ASR engine based upon the estimated persistence.

13. The system of claim 10, wherein adjusting the ASR engine is configurable to modify a lexicon used by the ASR engine.

14. The system of claim 10, wherein adjusting the ASR engine is configurable to adjust the recognition grammar used by the ASR engine.

15. The system of claim 10, wherein the ASR engine is configurable in response to a specificity of the one or more characteristics.