US 11,693,616 B2
Short segment generation for user engagement in vocal capture applications
Jon Moldover, San Francisco, CA (US); David Steinwedel, San Francisco, CA (US); Jeffrey C. Smith, Atherton, CA (US); and Perry R. Cook, Jacksonville, OR (US)
Assigned to Smule, Inc., San Francisco, CA (US)
Filed by SMULE, INC., San Francisco, CA (US)
Filed on Aug. 25, 2020, as Appl. No. 16/947,943.
Claims priority of provisional application 62/891,412, filed on Aug. 25, 2019.
Prior Publication US 2021/0055905 A1, Feb. 25, 2021
Int. Cl. G06F 3/0484 (2022.01); G06F 3/16 (2006.01); G06F 3/0482 (2013.01); G10L 25/51 (2013.01); G06F 3/0488 (2022.01); G10L 25/90 (2013.01)
CPC G06F 3/16 (2013.01) [G06F 3/0482 (2013.01); G06F 3/0484 (2013.01); G06F 3/0488 (2013.01); G10L 25/51 (2013.01); G10L 25/90 (2013.01); G06F 2203/04808 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A system comprising:
a service platform; and
plural media capture devices communicatively coupled via respective network communication interfaces to the service platform for media capture relative to a media encoding of an audio work, the media capture devices providing respective users thereof with a user interface for selecting from amongst performance capture options that include one or more partial portions of the audio work identified to the respective media capture devices by the service platform,
wherein the service platform identifies individual ones of the partial portions based on one or more of:
(i) musical structure coded for the audio work;
(ii) a machine learning algorithm applied to backing audio, vocal audio or lyrics of or corresponding to audiovisual performances captured against the audio work; and
(iii) crowd-sourced point- or portion-of-interest data measured for performer and/or non-performer user engagement with the audio work, and
wherein the media capture devices are configured to capture at least vocal audio of the respective users performed against audible renderings on the respective media capture devices of respectively selected partial portions of the audio work.