Method for locating an audio segment within an audio file

• US 20050131559A1
• Filed: 05/30/2003
• Published: 06/16/2005
• Est. Priority Date: 05/30/2002
• Status: Abandoned Application

• Current Assignee: Custom Speech USA, Inc.
• Original Assignee: Custom Speech USA, Inc.
• Inventors: Harbison, William II, Kahn, Jonathan, Huttinger, Michael C.
• Application Number:
  US10/516,374
• Publication Number:
  US 20050131559A1
• Time in Patent Office: Days
• US Class Current: 700/94
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

A method for locating an audio segment within an audio file comprising (i) providing a first transcribed text file associated with the audio file; (ii) providing a second transcribed text file associated with the audio file; (iii) receiving a user input defining a text segment corresponding to the audio segment to be located; (iv) searching for the text segment in the first transcribed text file; and (v) displaying only those occurrences of the text segment within the first transcribed text file that are also a match to occurrences of the text segment within the second transcribed text file.

Claims

1. A method for locating an audio segment within an audio file comprising:

(i) providing a first transcribed text file associated with the audio file;

(ii) providing a second transcribed text file associated with the audio file;

(iii) receiving a user input defining a text segment corresponding to the audio segment to be located;

(iv) searching for the text segment in the first transcribed text file; and

(v) displaying only those occurrences of the text segment within the first transcribed text file that are also a match to occurrences of the text segment within the second transcribed text file.

2. The method of claim 1 further comprising comparing the first transcribed text file to the second transcribed text file to determine each match and difference between the first transcribed text file and text segment in the second transcribed text file.

3. The method of claim 1 wherein the first transcribed text file is transcribed from the audio file using a first speech recognition software and the second transcribed text file is transcribed from the audio file using a second speech recognition software.

4. The method of claim 1 wherein the first transcribed text file is transcribed from the audio file using a first speech recognition software and the second transcribed text file is transcribed from the audio file by a human transcriptionist.

5. The method of claim 1 wherein displaying includes highlighting each match within the first transcribed text file being displayed in the first window.

6. The method of claim 1, wherein each of the matching occurrences of the text segment within the first transcribed text file are associated with one of a plurality of audio tags, each audio tag corresponding to one of a plurality of audio segments within the audio file.

7. The method of claim 6, wherein each of the matching occurrences of the text segment within the first transcribed text file are user-selectable to cause playback of the corresponding one of the plurality of audio segments within the audio file.