OPTIMIZED VIDEO SNAPSHOT

• US 20140327730A1
• Filed: 05/02/2013
• Published: 11/06/2014
• Est. Priority Date: 05/02/2013
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Wiener, Yair, Modai, Ori
• Granted Patent: US 9,609,272 B2
• Time in Patent Office: Days
• US Class Current: 348/14.09
• CPC Class Codes: G10L 25/57 for processing of video signals
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

Methods, media and devices for generating an optimized image snapshot from a captured sequence of persons participating in a meeting are provided. In some embodiments, methods media and devices for utilizing a captured image as a representative image of a person as a replacement of a video stream; as a representation of a person in offline archiving systems; or as a representation of a person in a system participant roster.

Claims

1. A method for presenting an aesthetic image, said method comprising:

analyzing an audio track of a user in a conference to determine when said user is an active speaker;

when said user is an active speaker, analyzing a speech signal of the audio track to identify aesthetic phonemes for when the user is an active speaker; and

determining at least one image of the user corresponding to said aesthetic phonemes.

2. The method of claim 1, said method further comprising receiving at an audio analysis tool a set of synchronized audio and video streams.

3. The method of claim 2, wherein said process of analyzing the speech signal of the audio track comprises classifying phonemes of the speech signal into at least two sets of phonemes.

4. The method of claim 3, wherein one of said at least two sets of phonemes is aesthetic phonemes.

5. The method of claim 2, said method further comprising refining said determined aesthetic image utilizing audio parameters of the audio track.

6. The method of claim 5, wherein said audio parameters comprise an estimation of the audio direction.

7. The method of claim 5, wherein said audio parameters comprise a background noise estimation.

8. The method of claim 5, wherein said audio parameters comprise cross talk detection.

9. The method of claim 2, said method further comprising analyzing video frames corresponding to said aesthetic phonemes to identify an aesthetically optimal image frame.

10. The method of claim 9, wherein said process of analyzing video frames is performed in background.

11. A system for presenting an aesthetic image, said system comprising:

an audio analysis tool enabled to analyze an audio track of a conference to determine when a participant to a conference is an active speaker, analyze a speech signal of the audio track to identify aesthetic phonemes of said active speaker, and determine at least one image of said active speaker corresponding to said aesthetic phonemes.

12. The system of claim 11, wherein said tool is further enabled to receive a set of synchronized audio and video streams.

13. The system of claim 12, wherein said analysis of the speech signal comprises classification of phonemes of the speech signal into at least two sets of phonemes.

14. The system of claim 13, wherein one of said at least two sets of phonemes is aesthetic phonemes.

15. The system of claim 12, wherein said tool is further enabled to refine said determination of the aesthetic image by utilizing audio parameters of the audio track.

16. The system of claim 15, wherein said audio parameters comprise an estimation of the audio direction.

17. The system of claim 15, wherein said audio parameters comprise a background noise estimation.

18. The system of claim 15, wherein said audio parameters comprise cross talk detection.

19. The system of claim 12, wherein said audio analysis tool is further enabled to analyze video frames corresponding to said aesthetic phonemes to identify an aesthetically optimal image frame.

20. The system of claim 19, wherein said analysis of video frames corresponding to said aesthetic phonemes to identify an aesthetically optimal image frame is performed in background.