US 11,810,585 B2
Systems and methods for filtering unwanted sounds from a conference call using voice synthesis
Rajendran Pichaimurthy, Karnataka (IN); and Madhusudhan Seetharam, Karnataka (IN)
Assigned to Rovi Guides, Inc., San Jose, CA (US)
Filed by Rovi Guides, Inc., San Jose, CA (US)
Filed on Aug. 10, 2022, as Appl. No. 17/884,851.
Application 17/884,851 is a continuation of application No. 17/015,832, filed on Sep. 9, 2020, granted, now 11,450,334.
Prior Publication US 2022/0383888 A1, Dec. 1, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 21/0208 (2013.01); G10L 21/0272 (2013.01); G10L 15/26 (2006.01); H04M 3/56 (2006.01); H04M 3/42 (2006.01); G10L 25/84 (2013.01)
CPC G10L 21/0208 (2013.01) [G10L 15/26 (2013.01); G10L 21/0272 (2013.01); G10L 25/84 (2013.01); H04M 3/42068 (2013.01); H04M 3/568 (2013.01); G10L 2021/02087 (2013.01); H04M 2203/5072 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
capturing a first voice signal, the first voice signal comprising a voice of a first user and a voice of a second user, by a first device, during a call;
preventing entirety of the first voice signal, the entirety of the first voice signal comprising the voice of the first user and the voice of the second user, from being transmitted into the call, wherein no part of the first voice signal is transmitted into the call;
converting the first voice signal into text;
generating a second voice signal based on portions of the text attributable to the voice of the first user; and
transmitting the second voice signal into the call.