Device for and method of language processing

• US 8,380,485 B1
• Filed: 08/13/2009
• Issued: 02/19/2013
• Est. Priority Date: 08/13/2009
• Status: Active Grant

• Current Assignee: The United States of America As Represented By The Director National Security Agency
• Original Assignee: The United States of America As Represented By The Director National Security Agency
• Inventors: Callahan, Susan E.
• Primary Examiner(s): GREGORY, BERNARR E
• Application Number:
  US12/460,906
• Time in Patent Office: 1,286 Days
• Field of Search: 726/1, 726/22, 380/1, 380/59, 704 1- 10, 704/200, 704270-278, 715/200, 715/209, 715/210
• US Class Current: 704/1
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04

Abstract

The present invention is a device for and method of language processing that includes a communication database of communications, a transcription database of transcripts for the communication, an extractor for extracting a visual representation of each communication, a first displayer for displaying a visual representation of a communication and its transcription, a segmentor for segmenting a visual representation, a media player, a first editor for blanking portions of a transcription and adding text, a second editor for filling in blanks and adding text, a second displayer for displaying a transcription that were blanked along with the corresponding entries made by the second editor and adding textual information, and a third displayer for providing feedback.

Claims

1. A device for language processing, comprising:

a) a communication database containing communications, having an output;

b) a transcription database containing a transcript for each communication in the communication database, where each character in a transcription is associated with a location in the format of the corresponding communication that is represented by the transcribed character, having an output for transmitting a transcript of a communication;

c) an extractor, having an output;

d) a first displayer, having a first input connected to the output of the text database, having a second input connected to the output of the extractor, having a third input, having a fourth input, having a fifth input, having a first output, having a second output, having a third output;

e) a segmentor, having an output connected to the third input of the first displayer;

f) a media player, having an input connected to the first output of the first displayer,

g) a first editor, having has an output connected to the fourth input of the first displayer;

h) a second editor, having an output connected to the fifth input of the first displayer;

i) a second displayer, having an input connected to the second output of the first displayer; and

j) a third displayer, having an input connected to the third output of the first displayer.

2. The device of claim 1, wherein said a communication database containing communications, where each communication in at least one format selected from the group of formats consisting of audio, video, graphic.

3. The device of claim 1, wherein said transcription database containing a transcript for each communication transcribed using characters selected from the group of characters consisting of letters and ideograms.

4. The device of claim 1, wherein said first displayer is a window on a computer that allows for insertion of hyperlinks to the Internet and to documents, highlighting, bolding, underlining, insertion of bullets, use of color, insertion of pictures and maps, tagging and linking of text/audio/video material, and copying, cutting, and pasting of text.

5. The device of claim 1, wherein said media player plays/displays media in formats selected from the group of formats consisting of mp3, .au, .mu, .wav, .jpg, .pdf, .bmp, .mp4, .mov, and .wmv.

6. The device of claim 1, wherein said media player accommodates unlimited audio file length, and includes audio manipulation features selected from the group of audio manipulation features consisting of speed rate changer, user expansion/compression of energy signal, forward/backward skipping with mouse or key strokes, looping by highlighting section of media, single or multi-channel audio/media input, independent volume control per channel, cropping, editing, inserting silence, foot pedal operation, separate volume control for each speaker, and muting.

7. A method of language processing, comprising the steps of:

a) receiving at least one communication, where each communication is in at least one format;

b) receiving a transcription for each received communication for which transcription is possible, where each character in a transcription is associated with a location in the format of the corresponding communication that is represented by the transcribed character;

c) extracting a visual representation of each communication received;

d) displaying a visual representation of a received communication and its transcription;

e) segmenting the visual representation of a selected communication, where each segment is uniquely identified, and where each location in the corresponding transcription is identified with the same identifier;

f) playing a communication, if possible;

g) editing a transcription of a communication;

h) filling in blanks in a transcription and adding textual information;

i) displaying edits to corresponding entries in transcription; and

j) providing feedback.

8. The method of claim 7, wherein said step of receiving at least one communication, where each communication is in at least one format is comprised of the step of receiving at least one communication, where each communication is in at least one format, where the format is selected from the group of formats consisting of audio, video, and graphic.

9. The method of claim 7, wherein said step of receiving a transcription for each received communication is comprised of the step of receiving a transcription for each received communication where each transcribed character is selected from the group of characters consisting of a letter and an ideogram.

10. The method of claim 7, wherein said step of extracting a visual representation of each communication received is comprised of the step of extracting a visual representation from the group of visual representations consisting of an energy waveform for audio for at least one speaker, a bar representing length of video and area of graphic.

11. The method of claim 7, wherein said step of displaying a visual representation of a received communication and its transcription is comprised of the step of displaying a visual representation in a window on a computer, where the transcription is displayed in any orthography, where the visual representation and transcription are navigated by selecting an area within the visual representation, clicking an area via a computer mouse, keyboard key, foot pedal, and any other suitable input device, where the transcription may be multilingual and in any font set and in any orthography or mixture of orthography, include hyperlinks to the Internet and to documents, picture, and maps, includes text highlighting, bolding, underlining, bullets, and color.

12. The method of claim 7, wherein said step of segmenting the visual representation of a selected communication is comprised of the step of segmenting the visual representation of a selected communication by uniquely identifying a segment with an identifier selected from the group of identifiers consisting of number, name, title, color, and graphic, assigning the identifier of a segment to the corresponding area in the transcription, and identifying areas in video with identifiers selected from the group of identifiers consisting of a mark, a highlight, and circles.

13. The method of claim 7, wherein said step of playing a communication, if possible is comprised of playing a communication in any format selected from the group of formats consisting of mp3, .au, .mu, .wav, .jpg, .pdf, .bmp, .mp4, .mov, and .wmv and manipulating the playing of a communication using a manipulation technique selected from the group of manipulation techniques consisting of speed rate changer, user expansion/compression of energy signal, forward/backward skipping, looping by highlighting section of communication, independent volume control per speaker, cropping, editing, inserting silence, foot pedal operation, and muting.

14. The method of claim 7, wherein said step of editing a transcription of a communication is comprised of the step of editing a transcription by replacing a portion of a transcription with a uniformly sized blank that may later be filled in with a correct response in user-definable format and color, where the blank is expandable to accommodate any response length, where the blank may concern a partial word, a single word, multiple words, and errorful text to be further edited and corrected, and where textual information may be added to a transcription to include glossaries, grammar notes, quizzes, comments, hints, and instructional guidance.

15. The method of claim 7, wherein said step of filling in blanks in a transcription and adding textual information is comprised of the step of filling in blanks in a transcription and adding textual information to blanks that expand to accommodate responses, tagging portions of the transcription for further review, grouping items, customizing view by number of columns, column width, column height, toolbar manipulation, font size, font type, font color, background color, cutting and pasting text, searching text, tagging text, and accessing on-line dictionaries.

16. The method of claim 7, wherein said step of displaying edits to corresponding entries in transcription is comprised of the step of displaying edits to corresponding entries in transcription using side-by-side comparison views with the expected responses.