Back to results
US 12,009,013 B2Granted
System and method for AI/XI based automatic song finding method for videos
AssigneeBellevue Investments GmbH & Co. Kgaa
InventorsDieter Rein, Jurgen Jaron
Life of this patent
Estimating the term…
Abstract
According to a first embodiment, one method presented herein involves methods of finding the best fitting song from a large audio database for a selected video production. The content of these songs utilized in the instant invention has been tagged by emotion tags describing the energy, the emotion of these songs over time—meaning that each song can contain a plurality of, even overlapping, emotions.
Claims4
A method of automatically matching one or more songs to a video, said video having a length associated therewith, comprising the steps of:
- (a) submitting said video to a video analysis tool, said video analysis tool automatically determining locations of scenes, segments, and objects in said video and assigning a plurality of time-varying emotion tags to said video;
- (b) in a computer, the processor performing the steps of:
- (i) determining an emotion level for each of said video scenes;
- (ii) calculating an energy level for each of said video scenes;
- (iii) determining one or more emotions associated with each of said video scenes;
- (iv) scaling each of said emotion values by a length of an associated tag;
- (v) determining a single value representative of all of said emotion values;
- (vi) searching an audio database containing a plurality of songs for one or more matching songs, each of said songs in said audio database having one or more emotion tags associated therewith, said emotion tags describing a time-varying energy and emotion of said song;
- (vii) select at least one song from said audio database based on said search;
- and (viii) adapting a length of said at least one song to match said video length, thereby automatically matching one or more songs to said video.
7 more elements
A method of matching at least one song to a video work selected by a user, wherein is provided an audio database containing a plurality of songs therein, each of said songs having at least a genre, an emotion, an energy level, and a length associated therewith, comprising the steps of:
- (a) submitting said video work to a video analysis tool, said video analysis tool automatically determining locations of scenes, segments, and objects in said video work and assigning a plurality of video tags to said video work, said plurality of tags being associated with said determined locations of scenes, segments, and objects of said video work;
- (b) in a computer, the processor performing the steps of:
- (i) using said video tags to determine cuts and transitions in said video work;
- (ii) using at least said cuts, transitions and said video tags to generate at least one video scene from said video work;
- (iii) determining an energy level for each of said at least one video scenes, thereby obtaining at least one energy level associated with said video work;
- (iv) determining a video emotion value associated with each of said video tags;
- (v) using said video tags to scale each of said video emotion values, thereby determining a main emotion of said video work;
- (vi) using each of said at least one energy levels associated with said video work to determine a dominant energy level of said video work;
- (vii) using said main emotion of said video work to determine a video genre;
- (viii) determining a length of said video work;
- (ix) using said main emotion of said video work, said length of said video work, said genre of said video work, and said dominant energy level of said video work to conduct a first search of said audio database for candidate songs;
- (1) if at least one candidate song is returned from said first search of said audio database, (ix1) presenting said at least one candidate songs to the user, and (ix2) allowing the user to select at least one of said at least one candidate songs, thereby matching at least one song to said video work;
- (x) if no candidate songs are returned from said first search of said audio database, using said main emotion of said video work, said length of said video work, and said genre of said video work to conduct a second search of said audio database for candidate songs;
- (xi) if at least one candidate song is returned from said second search of said audio database, (xi1) presenting said at least one candidate songs to the user, and (xi2) allowing the user to select at least one of said at least one candidate songs, thereby matching at least one song to said video work;
- (xii) if no candidate songs are returned from first search and from said second search of said audio database, using said main emotion of said video work and said length of said video work to conduct a third search of said audio database for candidate songs;
- (xiii) if at least one candidate song is returned from said third search of said audio database, (xiii1) presenting said at least one candidate songs to the user, and (xiii2) allowing the user to select at least one of said at least one candidate songs, thereby matching at least one song to said video work.
13 more elements
A method of matching at least one song to a video work selected by a user, wherein is provided an audio database containing a plurality of songs therein, each of said songs having at least a genre, an emotion, an energy level, and a length associated therewith, comprising the steps of:
- (a) submitting said video work to a video analysis tool, said video analysis tool automatically determining locations of scenes, segments, and objects in said video work and assigning a plurality of video tags to said video work, said plurality of tags being associated with said determined locations of scenes, segments, and objects of said video work;
- (b) in a computer, the processor performing the steps of:
- (i) using said video tags to determine cuts and transitions in said video work;
- (ii) using at least said cuts, transitions and said video tags to generate at least one video scene from said video work;
- (iii) determining an energy level for each of said at least one video scenes, thereby obtaining at least one energy level associated with said video work;
- (iv) determining a video emotion value associated with each of said video tags;
- (v) using said video tags to scale each of said video emotion values, thereby determining a main emotion of said video work;
- (vi) using each of said at least one energy levels associated with said video work to determine a dominant energy level of said video work;
- (vii) using said main emotion value and said video emotion values to search the audio database for a candidate song;
- (viii) adapting said candidate song to said video length;
- and (ix) applying said adapted candidate song to said video work, thereby matching said candidate song to said video work.
8 more elements
Dependencies are inferred from the claim text.