Method for form completion using speech recognition and text comparison

• US 20060167686A1
• Filed: 02/19/2004
• Published: 07/27/2006
• Est. Priority Date: 02/19/2003
• Status: Active Grant

• Current Assignee: Custom Speech USA, Inc.
• Original Assignee: Custom Speech USA, Inc.
• Inventors: Kahn, Jonathan
• Granted Patent: US 7,516,070 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/194 Calculation of difference between files
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A system and method for creating a final text from an audio file. This has particular utility in completing forms with speech-to-text conversion. The system and method includes transcribing the audio file into a transcribed text file using a speech recognition program. They further include comparing the transcribed text file with a previously created text file to determine differences between the transcribed text file and the previously created text file. Finally, the system and method includes correcting one of the transcribed text file or the previously created text file based upon the differences to create the final text.

Claims

1. A method for creating a final text from an audio file comprising:

(a) transcribing the audio file into a transcribed text file using a speech recognition program;

(b) comparing the transcribed text file with a previously created text file to determine differences between the transcribed text file and the previously created text file, where the previously created text file corresponds to a form; and

(c) correcting one of the transcribed text file or the previously created text file based upon the differences to create the final text.

2. The method of claim 1 further comprising:

(d) loading a first window with the transcribed text file; and

(e) loading a second window with the previously created text file.

3. The method of claim 2 further comprising:

(f) prior to comparing the transcribed text file with a previously created text file, modifying the text of the form to diminish the number of expected differences between the text in the transcribed text file and the previously created text file.

4. The method of claim 3 wherein modifying includes formatting a field name in the form such that only a first word in the field name is capitalized.

5. The method of claim 3 wherein modifying includes removing shell text that is not commonly dictated by a speaker.

6. The method of claim 5 wherein the shell text includes information contained in at least one of a header or a footer.

7. The method of claim 3 wherein modifying includes removing information corresponding to at least one of a transcriptionist'"'"'s name, date of transcription, speaker'"'"'s name, speaker'"'"'s place of employment.

8. The method of claim 3 wherein modifying includes inserting placeholder text into at least one field in the form.

9. The method of claim 3 further comprising:

(g) after correcting one of the transcribed text file or the previously created text file, modifying the final text to remove at least one of the modification made during step (f).

10. The method of claim 5 further comprising:

(h) adding shell text to the final text after correcting one of the transcribed text file or the previously created text file.

11. The method of claim 1 further comprising:

(i) generating multiple versions of the previously created text file, each of the multiple versions being based upon dictating characteristics of an intended speaker.

12. The method of claim 1 further comprising:

(j) extracting data from at least one field in the final text to a database

13. The method of claim 1 wherein the previously created text file includes text from a previously competed form.

14. The method of claim 1 wherein the previously created text file is determined by searching a number of previously created text files for text that is similar to text in the transcribed text file.

15. A system for creating a final text from an audio file comprising:

means for transcribing the audio file into a transcribed text file using a speech recognition program;

means for comparing the transcribed text file with a previously created text file to determine differences between the transcribed text file and the previously created text file, where the previously created text file corresponds to a form; and

means correcting one of the transcribed text file or the previously created text file based upon the differences to create the final text.

16. The system of claim 15 further comprising:

means for loading a first window with the transcribed text file; and

means for loading a second window with the previously created text file.

17. The system of claim 16 further comprising:

means for modifying the text of the form to diminish the number of expected differences between the text in the transcribed text file and the previously created text file prior to comparing the transcribed text file with a previously created text file.

18. The system of claim 17 further comprising:

means for modifying, after correcting one of the transcribed text file or the previously created text file, the final text to remove at least one of the modifications made to diminish the number of expected differences between the text in the transcribed text file and the previously created text file.

19. The system of claim 17 further comprising:

means for adding shell text to the final text after correcting one of the transcribed text file or the previously created text file.

20. The system of claim 15 further comprising:

means generating multiple versions of the previously created text file, each of the multiple versions being based upon dictating characteristics of an intended speaker.

21. The method of claim 15 further comprising:

means extracting data from at least one field in the final text to a database.

22. A system for creating a final text from an audio file comprising:

a storage device for storing the audio file;

a speech recognition engine to transcribe the audio file into a transcribed text file; and

a program that compares the transcribed text file with a previously created text file to determine differences between the transcribed text file and the previously created text file, and corrects one of the transcribed text file or the previously created text file based upon the differences to create the final text, where the previously created text file corresponds to a form.

23. The system of claim 22 wherein the program is capable of loading a first window with the transcribed text file and loading a second window with the previously created text file.

24. The system of claim 23 wherein the programs is capable of modifying the text of the form to diminish the number of expected differences between the text in the transcribed text file and the previously created text file prior to comparing the transcribed text file with a previously created text file.

25. The system of claim 24 wherein the program is capable of modifying the text by formatting a field name in the form such that only a first word in the field name is capitalized.

26. The system of claim 24 wherein the program is capable of modifying the text by removing shell text that is not commonly dictated by a speaker.

27. The system of claim 26 wherein the shell text includes information contained in at least one of a header or a footer.

28. The method of claim 23 wherein the program is capable of modifying the text by removing information corresponding to at least one of a transcriptionist'"'"'s name, date of transcription, speaker'"'"'s name, speaker'"'"'s place of employment.

29. The method of claim 23 wherein the program is capable of modifying the text by inserting placeholder text into least one field in the form.

30. The method of claim 23 wherein the program is capable of modifying the final text, after correcting one of the transcribed text file or the previously created text file, to remove at least one of the modification made to diminish the expected differences between the text in the transcribed text file and the previously created text file.

31. The method of claim 26 wherein the program is capable of adding shell text to the final text after correcting one of the transcribed text file or the previously created text file.

32. The method of claim 22 wherein the program is capable of generating multiple versions of the previously created text file, each of the multiple versions being based upon dictating characteristics of an intended speaker.

33. The method of claim 22 wherein the program is capable of extracting data from at least one field in the final text to a database

34. The method of claim 22 wherein the previously created text file includes text from a previously competed form.

35. The method of claim 22 wherein the program is capable of determining the previously created text file by searching a number of previously created text files for text that is similar to text in the transcribed text file.