US 12,133,064 B2
Video and audio splitting that simulates in-person conversations during remote conferencing
Brian Christman, Richardson, TX (US); Kamal D. Sharma, Mason, OH (US); Kevin A. Delson, Woodland Hills, CA (US); Robert R. Rosseland, Charlotte, NC (US); Amer Ali, Jersey City, NJ (US); and Gilbert Gatchalian, Union, NJ (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Sep. 29, 2022, as Appl. No. 17/955,736.
Prior Publication US 2024/0114311 A1, Apr. 4, 2024
Int. Cl. H04S 7/00 (2006.01); G06F 3/16 (2006.01); H04M 3/56 (2006.01); H04S 1/00 (2006.01)
CPC H04S 7/304 (2013.01) [G06F 3/165 (2013.01); H04M 3/568 (2013.01); H04S 1/007 (2013.01); H04S 2400/11 (2013.01); H04S 2400/13 (2013.01); H04S 2400/15 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A method for simulating an in-person audio conversation during a videotelephony conference, the method comprising:
detecting a first audio input provided by a first participant;
detecting a second audio input provided by a second participant;
positioning the first participant in a first region of a videotelephony conference interface presented to a listener;
positioning the second participant in a second region of the videotelephony conference interface; and
adjusting an audio output provided to the listener based on positions of the first and second participants in the videotelephony conference interface, the adjusting further comprising:
dynamically mixing a first audio output based on the first and second audio inputs;
dynamically mixing a second audio output based on the first and second audio inputs;
outputting the first audio output to the listener through a first audio channel; and
outputting the second audio output to the listener through a second audio channel; and
the method further comprising:
detecting a third audio input from the listener; and
in response to the third audio input, remixing the first and second audio outputs.