Patent · US Active

System and method for determining the active talkers in a video conference

US9154730B2 · kind B2 · utility

8Cited by
1References
22Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 16, 2009
Grant dateOct 6, 2015
Priority date
Expiry dateJul 27, 2032

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04N21/4788
  • WIPO fieldAudio-visual technology
  • WIPO sectorElectrical engineering

Abstract

The present invention describes a method of determining the active talker for display on a video conferencing system, including the steps of: for each participant, capturing audio data using an audio capture sensor and video data using a video capture sensor; determining the probability of active speech (pA, pB . . . pN), where the probability of active speech is a function of the probability of soft voice detection captured by the audio capture sensor and the probability of lip motion detection captured by the video capture sensor; and automatically displaying at least the participant that has the highest probability of active speech.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.