Universal guide track

• US 20030049015A1
• Filed: 09/12/2001
• Published: 03/13/2003
• Est. Priority Date: 09/12/2001
• Status: Active Grant

• Current Assignee: DUB Synchro, Inc.
• Original Assignee: Ryshco Media Inc.
• Inventors: Ryshpan, Howard, Cote, Jocelyne
• Granted Patent: US 7,343,082 B2
• Time in Patent Office: Days
• US Class Current: 386/54
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/10 Indexing; Addressing; Timing or synchronising; Measuring tape travel
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D

Abstract

A method and apparatus is disclosed which provides an efficient tool for performing post-production synchronization of a video source. In the preferred embodiment, the graphemes of a detected audio source are synchronized with a script and are shown through a user interface. The user interface enables a user to perform the post-synchronization easily.

Claims

1. An editing tool for performing post-production synchronization on a video source, the video source comprising an audio source, the editing tool comprising:

a speech recognition associating unit collecting and associating basic units of recognized speech and related time codes received from a speech recognition module,

a user interface providing an indication of the current temporal location of a post-production audio recording to be synchronized with the video source with respect to a script corresponding to the audio source using the basic units of recognized speech and related time codes from the speech recognition associating unit.

2. The editing tool for performing post-production synchronization on a video source as claimed in claim 1, wherein the basic units of recognized speech received from the speech recognition module are phonemes, the editing tool further comprising a converting unit, the converting unit converting the phonemes and the related time codes from the speech recognition module into words and related time codes;

the user interface providing an indication of the current temporal location of the post-production audio recording with respect to a script corresponding to the audio source using the words and the related time codes.

3. The editing tool for performing post-production synchronization on a video source as claimed in claim 2, further comprising a phoneme to grapheme conversion module, converting the phonemes and the related time codes from the speech recognition module into graphemes and related time codes, the user interface providing an indication of the current temporal location of a post-production audio recording to be synchronized with the video source with respect to a script corresponding to the audio source using the graphemes and the related time codes received from the phoneme to grapheme conversion module.

4. The editing tool as claimed in claim 2, further comprising a word to phoneme database, providing a list of words and their corresponding phonemes, the word to phoneme database connected to the converting unit, the speech recognition module providing words and related time codes, the user interface enabling a synchronization of the words of the script with words detected in the post-production audio recording using the phoneme to word database, the phonemes and the related time codes.

5. The editing tool as claimed in claim 2, wherein the user interface enables a synchronization of the beginning and the end of each phrase of the script and the post-production audio recording using at least the phonemes and the related time codes.

6. The editing tool as claimed in claim 4, further comprising a conformed text source, providing the conformed text to the speech recognition module, the user interface synchronizing the words of the script with the words of the conformed text source using the phoneme to word database, the phonemes and the related time codes, and the conformed text source.

7. The editing tool as claimed in claim 3, further comprising a conformed text source connected to the phoneme to grapheme conversion module, the phoneme to grapheme conversion module providing graphemes and time codes using the conformed text, the user interface enabling a synchronization of the graphemes from the audio source with the script.

8. The editing tool as claimed in claim 1, wherein the time codes related to the script may be edited.

9. The editing tool as claimed in claim 1, further comprising an actor name generator;

the speech recognition associating unit further receives a parameter indicative of the speaker from the speech recognition module, the parameter being associated with the name of an actor using the actor name generator;

the user interface displaying the script according to the name of the actor.

10. The editing tool as claimed in claim 1, further comprising a database, storing data of the user interface, the data stored comprising the time codes associated with the script.

11. The editing tool as claimed in claim 8, further comprising a database, storing data of the user interface, the data stored comprising the time codes associated with the script.

12. The editing tool as claimed in claim 1, wherein the user interface comprises a navigation window enabling to change the current temporal location.

13. The editing tool as claimed in claim 1, wherein the user interface comprises a video window, the video window comprising the video source.

14. The editing tool as claimed in claim 9, wherein the script is displayed in different windows in the user interface according to the name of the actor.

15. The editing tool as claimed in claim 1, wherein the basic units of recognized speech are presented by the user interface with a visual indication of their temporal properties using their related time codes.

16. The editing tool as claimed in claim 15, wherein the visual indication of their temporal properties by the user interface comprises the use of colors, each color being associated with a range of temporal duration.

17. The editing tool as claimed in claim 15, wherein the visual indication of their temporal properties by the user interface comprises the use of extendable font.

18. A method for performing a post-production synchronization on a video source, the method comprising the steps of:

providing a sound source of the video source;

providing the sound source to a voice recognition module;

receiving basic units of recognized speech and time codes from the voice recognition module;

processing the basic units of recognized speech and the time codes to provide an indication of the current temporal location of a post-production audio recording to be synchronized with the video source with respect to a script corresponding to the audio source using the basic units of recognized speech and the time codes.

19. The method as claimed in claim 18, further comprising the step of converting the basic units of recognized speech received with the time codes from the voice recognition module into words and related time codes, the words and the related time codes being processed to provide an indication of the current temporal location of a post-production audio recording to be synchronized.

20. The method as claimed in claim 18, further comprising the step of converting the basic units of recognized speech received with the time codes from the voice recognition module into graphemes and related time codes, the graphemes and the related time codes being processed to provide an indication of the current temporal location of a post-production audio recording to be synchronized.

21. The method as claimed in claim 18, wherein the basic units of recognized speech are phonemes.

22. The method as claimed in claim 18, further comprising the step of providing a conformed text source, the processing of the basic units of recognized speech and the time codes being performed using the basic units of recognized speech, the time codes and the conformed text source.

23. The method as claimed in claim 21, further comprising the step of amending at least one part of the sound source and the time codes using the detected graphemes with an indication of the current temporal location in the sound source of the video source.