Techiques for model optimization for statistical pattern recognition

• US 20070112567A1
• Filed: 11/07/2006
• Published: 05/17/2007
• Est. Priority Date: 11/07/2005
• Status: Abandoned Application

• Current Assignee: ScanScout, Inc. (Magnite, Inc.)
• Original Assignee: ScanScout, Inc. (Magnite, Inc.)
• Inventors: Lee, Steven, Lau, Wai
• Application Number:
  US11/594,717
• Publication Number:
  US 20070112567A1
• Time in Patent Office: Days
• US Class Current: 704/240
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0207 Discounts or incentives, e.g. coupons or rebates
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: G06Q 30/0252 based on events or environment, e.g. weather or festivals
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0261 based on user location
• CPC Class Codes: G06Q 30/0264 based upon schedule
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06V 10/768 using context analysis, e.g. recognition aided by known co-occurring patterns
• 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

Abstract

In one embodiment, a statistical pattern recognition engine determines content for a statistical pattern recognition task. The content and/or information related to the content is analyzed to determine a model to use in the statistical pattern recognition. For example, models may be classified in a plurality of domains based on different sets of data used to train models in the domain. The models may be classified based on knowledge sources used to generate the models, such as a news knowledge source, entertainment knowledge source, business knowledge source, etc. A model in the plurality of models is then determined based on the analysis where the determined model is classified in a domain. The model is then used by the statistical pattern recognition engine to perform the statistical pattern recognition task. For example, spoken words are transcribed into text using the determined model.

Claims

1. A method for determining a model for a statistical pattern recognition engine, the method comprising:

determining content for analysis by the statistical pattern recognition engine;

analyzing the content and/or information related to the content to determine a model in a plurality of models, wherein the determined model is classified in a domain in a plurality of domains, the domain including one or more models trained using information determined to include similar characteristics to the content; and

providing the determined model to the statistical pattern recognition engine for statistical pattern recognition.

2. The method of claim 1, wherein the statistical pattern recognition engine is configured to perform a statistical pattern recognition analysis on the content using the determined model.

3. The method of claim 2, further comprising adapting the determined model in real-time based on the content and/or the information related to the content before providing the determined model to the statistical pattern recognition engine.

4. The method of claim 1, further comprising:

determining one or more additional models based on the analysis; and

providing the one or more additional models to the statistical pattern recognition engine for the statistical pattern recognition.

5. The method of claim 1, further comprising:

determining information related to a domain in the plurality of domains; and

modifying a model in the plurality of models associated with the domain based on the information.

6. The method of claim 5, further comprising normalizing the information before modifying the model.

7. The method of claim 1, wherein domains in the plurality of domains are associated with different knowledge sources.

8. The method of claim 1, wherein models in the plurality of domains are training used different sets of data that include different characteristics.

9. The method of claim 1, wherein the determined model comprises a speaking style model and/or time extension model.

10. The method of claim 1, wherein the statistical pattern recognition comprises speech recognition.

11. A method for determining a model for a statistical pattern recognition engine, the method comprising:

receiving a plurality of files, each file including rich media content;

for each of the files, performing the following;

analyzing the content in the file and/or information related to the content to determine a domain that is determined to include similar characteristics to the content;

determining a model in the determined domain based on the content in the file and/or information related to the content; and

providing the determined model to the statistical pattern recognition engine for analysis.

12. The method of claim 11, wherein models in the plurality of domains are training used different sets of data that include different characteristics.

13. The method of claim 11, wherein the statistical pattern recognition comprises speech recognition.

14. An apparatus configured to determine a model for a statistical pattern recognition engine, the apparatus comprising:

one or more processors; and

logic encoded in one or more tangible media for execution by the one or more processors and when executed operable to;

determine content for analysis by the statistical pattern recognition engine;

analyze the content and/or information related to the content to determine a model in a plurality of models, wherein the determined model is classified in a domain in a plurality of domains, the domain including one or more models trained using information determined to include similar characteristics to the content; and

provide the determined model to the statistical pattern recognition engine for statistical pattern recognition.

15. The apparatus of claim 14, wherein the statistical pattern recognition engine is configured to perform a statistical pattern recognition analysis on the content using the determined model.

16. The apparatus of claim 15, wherein the logic when executed is further operable to adapt the determined model in real-time based on the content and/or the information related to the content before providing the determined model to the statistical pattern recognition engine.

17. The apparatus of claim 14, wherein the logic when executed is further operable to:

determine one or more additional models based on the analysis; and

provide the one or more additional models to the statistical pattern recognition engine for the statistical pattern recognition.

18. The apparatus of claim 14, wherein the logic when executed is further operable to:

determine information related to a domain in the plurality of domains; and

modify a model in the plurality of models associated with the domain based on the information.

19. The apparatus of claim 18, wherein the logic when executed is further operable to normalize the information before modifying the model.

20. The apparatus of claim 14, wherein domains in the plurality of domains are associated with different knowledge sources.

21. The apparatus of claim 14, wherein models in the plurality of domains are training used different sets of data that include different characteristics.

22. The apparatus of claim 14, wherein the determined model comprises a speaking style model and/or time extension model.

23. The apparatus of claim 14, wherein the statistical pattern recognition comprises speech recognition.

24. An apparatus configured to determine a model for a statistical pattern recognition engine, the apparatus comprising:

one or more processors; and

logic encoded in one or more tangible media for execution by the one or more processors and when executed operable to;

receive a plurality of files, each file including rich media content;

for each of the files, the logic when executed is further operable to;

analyze the content in the file and/or information related to the content to determine a domain that is determined to include similar characteristics to the content;

determine a model in the determined domain based on the content in the file and/or information related to the content; and

provide the determined model to the statistical pattern recognition engine for analysis.

25. The apparatus of claim 24, wherein models in the plurality of domains are training used different sets of data that include different characteristics.

26. The apparatus of claim 24, wherein the statistical pattern recognition comprises speech recognition.