US 12,279,022 B2
Generating translated media streams
Ben Avi Ingel, Binyamina (IL); and Ron Zass, Kiryat Tivon (IL)
Filed by Ben Avi Ingel, Binyamina (IL); and Ron Zass, Kiryat Tivon (IL)
Filed on Apr. 23, 2024, as Appl. No. 18/643,486.
Application 18/643,486 is a continuation of application No. 18/097,900, filed on Jan. 17, 2023, granted, now 12,010,399.
Application 18/097,900 is a continuation of application No. 17/460,644, filed on Aug. 30, 2021, granted, now 11,595,738, issued on Feb. 28, 2023.
Application 17/460,644 is a continuation of application No. 16/813,984, filed on Mar. 10, 2020, granted, now 11,140,459, issued on Oct. 5, 2021.
Claims priority of provisional application 62/822,856, filed on Mar. 23, 2019.
Claims priority of provisional application 62/816,137, filed on Mar. 10, 2019.
Prior Publication US 2024/0276072 A1, Aug. 15, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 21/475 (2011.01); G06F 40/58 (2020.01); G10L 13/00 (2006.01); G10L 13/033 (2013.01); G10L 13/08 (2013.01); G10L 13/10 (2013.01); H04N 21/266 (2011.01); H04N 21/2668 (2011.01); H04N 21/458 (2011.01); H04N 21/81 (2011.01)
CPC H04N 21/8126 (2013.01) [G06F 40/58 (2020.01); G10L 13/00 (2013.01); G10L 13/033 (2013.01); G10L 13/086 (2013.01); G10L 13/10 (2013.01); H04N 21/2668 (2013.01); H04N 21/458 (2013.01); H04N 21/4755 (2013.01)] 53 Claims
OG exemplary drawing
 
1. A computer program product for artificially generating translated media streams, the computer program product embodied in a non-transitory computer-readable medium and including instructions that when executed by at least one processor cause the at least one processor to execute a method comprising:
receiving a media stream of an individual speaking in an origin language, wherein the individual is associated with a particular voice;
analyzing the received media stream to determine characteristics of the particular voice of the individual;
determining a synthesized voice based on the determined characteristics of the particular voice of the individual, wherein the synthesized voice sounds substantially identical to the particular voice; and
generating a translated media stream that includes, for each word spoken in the origin language in the received media stream, a respective at least one word in a target language articulated using the synthesized voice.