System and method for editing recorded videoconference data

• US 9,247,205 B2
• Filed: 08/31/2010
• Issued: 01/26/2016
• Est. Priority Date: 08/31/2010
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Marvit, David L.
• Primary Examiner(s): Dang, Hung
• Assistant Examiner(s): Wendmagegn, Girumsew
• Application Number:
  US12/872,319
• Publication Number:
  US 20120051719A1
• Time in Patent Office: 1,974 Days
• Field of Search: 386/235, 386/285, 386/278, 348/14.08
• US Class Current: 1/1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: H04N 7/155 involving storage of or access to video conference sessions tracking arrangements for later retrieval of a computer conference content or participants activities H04L12/1831

Abstract

In a method embodiment, a method for automatically editing data recorded during a videoconference includes accessing a plurality of video data streams. Each video data stream records a view of at least one of a plurality of human participants of the videoconference. The view recorded by each video data stream is different from the view recorded by each other video data stream. The method further includes determining, using one or more processors executing logic, that one of the plurality of video data streams recorded a view of a first one of the plurality of participants while the first one of the plurality of participants made a first statement. In addition the method includes determining, using one or more processors executing logic, that one of the plurality of video data streams recorded a view of a second one of the plurality of participants while the second one of the plurality of participants made a second statement after the first one of the plurality of participants made the first statement. An edited video data stream is generated using the plurality of video data streams. The edited video data stream comprises a transition that switches from the view of the first one of the plurality of participants to the view of the second one of the plurality of participants. The transition is timed such that when the edited video data stream is played the transition occurs before the commencement of the second statement.

Claims

1. A method for automatically editing data recorded during a videoconference, comprising:

accessing a plurality of video data streams, each video data stream recording a view of at least one of a plurality of human participants of the videoconference, the view recorded by each video data stream being different from the view recorded by each other video data stream;

determining, using one or more processors executing logic, that one of the plurality of video data streams recorded a view of a first one of the plurality of participants while the first one of the plurality of participants made a first statement;

determining, using one or more processors executing logic, that one of the plurality of video data streams recorded a view of a second one of the plurality of participants while the second one of the plurality of participants made a second statement after the first one of the plurality of participants made the first statement; and

generating an edited video data stream using the plurality of video data streams, the edited video data stream comprising a transition that switches from the view of the first one of the plurality of participants to the view of the second one of the plurality of participants, the transition timed such that when the edited video data stream is played the transition occurs before the commencement of the second statement, wherein the transition is based at least in part on a determination that one of the plurality of participants is more important than another one of the plurality of participants, and wherein the determination that one of the plurality of participants is more important than another one of the plurality of participants is based at least in part on which participant of the plurality of participants contribute the most human speech content during the entire videoconference.

2. The method of claim 1, further comprising determining when, relative to one of the plurality of video data streams, the first statement ends.

3. The method of claim 2, wherein the determination of when the first statement ends is based at least in part on one or more audio data streams recorded during the videoconference.

4. The method of claim 2, wherein the determination of when the first statement ends is based at least in part on a determination that audio data of one or more audio data streams recorded during the videoconference comprises an audio interruption made my one of the plurality of participants during the first statement, the end of the first statement occurring after the audio interruption.

5. The method of claim 1, further comprising determining when, relative to one of the plurality of video data streams, the second statement begins.

6. A non-transitory computer-readable memory storing logic, the logic operable when executed by one or more processors to:

access a plurality of video data streams, each video data stream recording a view of at least one of a plurality of human participants of the videoconference, the view recorded by each video data stream being different from the view recorded by each other video data stream;

determine that one of the plurality of video data streams recorded a view of a first one of the plurality of participants while the first one of the plurality of participants made a first statement;

determine that one of the plurality of video data streams recorded a view of a second one of the plurality of participants while the second one of the plurality of participants made a second statement after the first one of the plurality of participants made the first statement; and

generate an edited video data stream using the plurality of video data streams, the edited video data stream comprising a transition that switches from the view of the first one of the plurality of participants to the view of the second one of the plurality of participants, the transition timed such that when the edited video data stream is played the transition occurs before the commencement of the second statement, wherein the transition is based at least in part on a determination that one of the plurality of participants is more important than another one of the plurality of participants, and wherein the determination that one of the plurality of participants is more important than another one of the plurality of participants is based at least in part on which participant of the plurality of participants contribute the most human speech content during the entire videoconference.

7. The non-transitory computer-readable memory of claim 6, wherein the logic is further operable when executed by the one or more processors to determine when, relative to one of the plurality of video data streams, the first statement ends.

8. The non-transitory computer-readable memory of claim 7, wherein the determination of when the first statement ends is based at least in part on one or more audio data streams recorded during the videoconference.

9. The non-transitory computer-readable memory of claim 7, wherein the determination of when the first statement ends is based at least in part on a determination that audio data of one or more audio data streams recorded during the videoconference comprises an audio interruption made my one of the plurality of participants during the first statement, the end of the first statement occurring after the audio interruption.

10. The non-transitory computer-readable memory of claim 6, wherein the logic is further operable when executed by the one or more processors to determine, relative to one of the plurality of video data streams, the second statement begins.

11. A system comprising:

one or more processors; and

computer-readable memory comprising logic, the logic operable when executed by the one or more processors to;

access a plurality of video data streams, each video data stream recording a view of at least one of a plurality of human participants of the videoconference, the view recorded by each video data stream being different from the view recorded by each other video data stream;

determine that one of the plurality of video data streams recorded a view of a first one of the plurality of participants while the first one of the plurality of participants made a first statement;

determine that one of the plurality of video data streams recorded a view of a second one of the plurality of participants while the second one of the plurality of participants made a second statement after the first one of the plurality of participants made the first statement; and

generate an edited video data stream using the plurality of video data streams, the edited video data stream comprising a transition that switches from the view of the first one of the plurality of participants to the view of the second one of the plurality of participants, the transition timed such that when the edited video data stream is played the transition occurs before the commencement of the second statement, wherein the transition is based at least in part on a determination that one of the plurality of participants is more important than another one of the plurality of participants, and wherein the determination that one of the plurality of participants is more important than another one of the plurality of participants is based at least in part on which participant of the plurality of participants contribute the most human speech content during the entire videoconference.

12. The system of claim 11, wherein the logic is further operable when executed by the one or more processors to determine when, relative to one of the plurality of video data streams, the first statement ends.

13. The system of claim 12, wherein the determination of when the first statement ends is based at least in part on one or more audio data streams recorded during the videoconference.

14. The system of claim 12, wherein the determination of when the first statement ends is based at least in part on a determination that audio data of one or more audio data streams recorded during the videoconference comprises an audio interruption made my one of the plurality of participants during the first statement, the end of the first statement occurring after the audio interruption.