System and method for dynamic ASR based on social media
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.
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.