US 12,327,572 B2
Systems and methods for generating trailers (summaries) for audio content using a short rolling time window
Xingran Zhu, Stockholm (SE); Jussi Jerker Karlgren, Stockholm (SE); and Md. Iftekhar Tanveer, Revere, MA (US)
Assigned to Spotify AB, Stockholm (SE)
Filed by Spotify AB, Stockholm (SE)
Filed on Jun. 30, 2022, as Appl. No. 17/855,637.
Claims priority of provisional application 63/217,603, filed on Jul. 1, 2021.
Prior Publication US 2023/0005497 A1, Jan. 5, 2023
Int. Cl. G10L 25/63 (2013.01); G06F 16/9535 (2019.01); G06F 40/20 (2020.01); G10L 15/04 (2013.01); G10L 15/22 (2006.01); G10L 25/30 (2013.01); G10L 25/45 (2013.01); H04L 12/18 (2006.01)
CPC G10L 25/63 (2013.01) [G10L 15/04 (2013.01); G10L 15/22 (2013.01); G10L 25/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
at an electronic device:
receiving an audio file;
dividing the audio file into a plurality of segments;
automatically, without user input, determining, for each respective segment, a descriptor from a plurality of descriptors and a value of the descriptor for the segment, wherein determining the descriptor for each respective segment comprises:
applying a rolling time window to the respective segment to generate a set of descriptors, each descriptor in the set of descriptors corresponding to a respective time window of the respective segment, wherein the rolling time window is shorter than a length of the respective segment;
selecting one or more segments, less than all, of the plurality of segments, based on a comparison of the respective values of respective descriptors for respective segments and genre-specific criteria selected based on a genre of the audio file; and
generating a summarized version of the audio file by arranging the selected one or more segments.