METHOD AND SYSTEM FOR CONVERTING AUDIO TEXT FILES ORIGINATING FROM AUDIO FILES TO SEARCHABLE TEXT AND FOR PROCESSING THE SEARCHABLE TEXT

• US 20130041892A1
• Filed: 10/15/2012
• Published: 02/14/2013
• Est. Priority Date: 10/13/2006
• Status: Active Grant

• Current Assignee: Syscom Incorporated (Teijin Limited)
• Original Assignee: Syscom Incorporated (Teijin Limited)
• Inventors: Bayer, Theodore F., Adkins, Donald R., Corbin, Gregory A.
• Granted Patent: US 9,020,811 B2
• Time in Patent Office: Days
• US Class Current: 707/722
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00

Abstract

A system and method for processing audio text files includes a content repository storing audio text files. A text transformer linguistically analyzes the audio text files within a content of multiple lexicons to form edited text results and creates a reflection repository having reflection files therein corresponding to the audio text files from the edited text results. A search engine searches the reflection files and a user device displays a first reflection file from the reflection files or a first audio text file from the audio files in response to searching.

Claims

1. A method of processing audio text files generated from audio files comprising:

linguistically analyzing the audio text files within a context of multiple lexicons to form edited text results;

creating reflection files corresponding to the audio text files from the edited text results;

storing the reflection files in a reflection repository;

processing the reflection files; and

displaying a first reflection file from the reflection files or a first audio text file from the audio text files in response to processing.

2. A method as recited in claim 1 wherein processing comprises searching the reflection files.

3. A method as recited in claim 1 wherein processing comprises text analyzing the reflection files.

4. A method as recited in claim 1 wherein text analyzing comprises generating an index.

5. A method as recited in claim 1 further comprising storing the audio text files in a content repository prior to linguistically analyzing.

6. A method as recited in claim 5 further comprising storing metadata associated with the audio text files in the content repository.

7. A method as recited in claim 1 wherein the multiple lexicons include custom lexicons.

8. A method as recited in claim 1 further comprising grammatically analyzing the edited text.

9. A method as recited in claim 1 further comprising spell checking the edited text.

10. A method as recited in claim 1 further comprising displaying a plurality of search results in response to searching.

11. A method as recited in claim 10 further comprising selecting a first search result from the plurality of search results and wherein displaying comprises displaying the first reflection file from the reflection files or the first audio text file from the audio text files in response to processing and selecting.

12. A method as recited in claim 1 wherein displaying a first reflection file from the reflection files or a first audio text file comprises displaying the first reflection file and the first audio text file.

13. A method as recited in claim 1 wherein the reflection repository and a content repository storing the audio text files are co-located.

14. A method as recited in claim 1 further comprising linking a first audio text file and the first reflection file in a content repository.

15. A method as recited in claim 1 further comprising linking a first audio text image and the first reflection file in a content repository with a security setting of the first audio text file.

16. A method as recited in claim 1 further comprising forming a search index from the reflected files and wherein processing comprises searching the search index.

17. A method as recited in claim 16 further comprising deleting the audio text files after forming the search index.

18. A method as recited in claim 1 further comprising associating metadata with each of the audio text files.

19. A method as recited in claim 18 further comprising naming each audio text file in response to the respective metadata.

20. A method as recited in claim 19 wherein searching comprises searching content of each audio text file and the metadata.

21. A method as recited in claim 1 further comprising translating the audio text files from a first language to a second language.

22. A system for processing audio text files generated from audio files comprising:

text transformer linguistically analyzing the audio text files within a context of multiple lexicons to form edited text results, and creating reflection files corresponding to the audio text files from the edited text results;

a reflection repository storing the reflection files therein;

a processing tool processing the reflection files; and

a user device displaying a first reflection file from the reflection files or a first audio text file from the audio text files in response to processing.

23. A system as recited in claim 22 further comprising a content repository storing the audio text files therein.

24. A system as recited in claim 23 wherein the reflection repository and the content repository are co-located.

25. A system as recited in claim 23 wherein the text transformer stores the reflection files in the content repository.

26. A system as recited in claim 23 wherein the content repository stores metadata associated with the audio text files.

27. A system as recited in claim 22 wherein the multiple lexicons include custom lexicons for a particular application.

28. A system as recited in claim 22 wherein the text transformer further grammatically analyzes the audio text files to form the edited text results.

29. A system as recited in claim 22 wherein the text transformer further spell checks the audio text files to form the edited text results.

30. A system as recited in claim 22 wherein the user device displays a plurality of search results in response to searching.

31. A system as recited in claim 30 wherein the user device selects a first search result from the plurality of search results and displays the first reflection file or the first audio text file.

32. A system as recited in claim 22 wherein the user device displays a first reflection file from the reflection files and a first audio file.

33. A system as recited in claim 22 wherein the text transformer links a first audio text file and a first reflection file in a content repository.

34. A system as recited in claim 22 wherein the text transformer links a first audio text file and a first reflection file in a content repository with a security setting of the first audio text file.

35. A system as recited in claim 22 wherein the processing tool forms a search index from the reflection files and searches the search index.

36. A system as recited in claim 22 wherein the user device displays a search bar for inputting search terms into the processing tool.

37. A system as recited in claim 22 further comprising a translation module translating the audio text file and communicating the audio text file to the text transformer.

38. A method of processing optical character recognition results of image text documents comprising:

linguistically analyzing the optical character recognition results within a context of multiple lexicons to form edited text results;

creating reflection files corresponding to the image text documents from the edited text results;

storing the reflection files in a reflection repository;

processing the reflection files; and

displaying a first reflection file from the reflection files or a first image text document from the image text documents in response to processing.

39. A method as recited in claim 38 wherein processing comprises searching the reflection files.

40. A method as recited in claim 38 wherein processing comprises text analyzing the reflection files.

41. A method as recited in claim 38 wherein text analyzing comprises generating an index.

42. A method as recited in claim 38 further comprising storing the image text documents in a content repository prior to performing optical character recognition.

43. A method as recited in claim 42 further comprising storing metadata associated with the image text documents in the content repository.

44. A method as recited in claim 38 wherein the multiple lexicons include custom lexicons.

45. A method as recited in claim 38 further comprising grammatically analyzing the optical character recognition results to form the edited text results.

46. A method as recited in claim 38 further comprising spell checking the optical character recognition results to form the edited text results.

47. A method as recited in claim 38 further comprising displaying a plurality of search results in response to processing.

48. A method as recited in claim 47 further comprising selecting a first search result from the plurality of search results and wherein displaying comprises displaying the first reflection file from the reflection files or the first image document from the image documents in response to processing and selecting.

49. A method as recited in claim 38 wherein displaying a first reflection file from the reflection files or a first image document comprises displaying the first reflection file and the first image text document.

50. A method as recited in claim 38 wherein the reflection repository and the content repository are co-located.

51. A method as recited in claim 38 further comprising linking a first text image and a first reflection file in the content repository.

52. A method as recited in claim 38 further comprising linking a first text image and the first reflection file in the content repository with a security setting of the first text image.

53. A method as recited in claim 38 further comprising forming a search index from the reflected files and wherein processing comprises processing the search index.

54. A method as recited in claim 53 further comprising deleting the text documents after forming an index.

55. A method as recited in claim 38 further comprising associating metadata with each of the image text documents.

56. A method as recited in claim 55 further comprising naming each image text document in response to the respective metadata.

57. A method as recited in claim 56 wherein searching comprises searching the content of each image text documents and the metadata.

58. A method as recited in claim 38 further comprising translating the audio text file from a first language to a second language.