Back to results
US 9,753,925 B2Granted
Systems, methods, and apparatus for generating an audio-visual presentation using characteristics of audio, visual and symbolic media objects
AssigneeGracenote, Inc.
InventorsMarkus K. Cremer, Ching-Wei Chen, Peter C. DiMaria, Ho-Hsiang Wu
Life of this patent
Estimating the term…
Abstract
In an embodiment, a method and apparatus for generating a presentation is provided. The method considers characteristics of audio works and visual works when constructing the presentation. In some embodiments, the presentation may be automatically constructed.
Claims18
A method of creating an audio-visual presentation, the method comprising:
- identifying a first plurality of media object characteristics associated with a first media object to be presented by a media player device, the first media object including audio data, and the first plurality of media object characteristics including a mood characteristic of the audio data;
- determining a congruency between the first plurality of media object characteristics and a second plurality of media object characteristics associated with a second media object that includes video data, the determining of the congruency including accessing a score representative of a degree of congruency between one of the first plurality of media object characteristics and one of the second plurality of media object characteristics, the score being accessed from a correlation matrix, the determining of the congruency being based on the score and a threshold value;
- determining a plurality of temporal segments of the audio data based on the mood characteristic;
- determining a duration of a temporal segment of the plurality of temporal segments of the audio data;
- identifying the second media object from a plurality of reference media objects based on the congruency between the first plurality of media object characteristics and the second plurality of media object characteristics, the identifying of the second media object being further based on the duration of the temporal segment of the audio data;
- and
- using a processor, generating the audio-visual presentation to synchronously present the first media object and the second media object on the media player device.
4 more elements
A system comprising:
- a memory having instructions embodied thereon;
- and
- one or more processors configured by the instructions to perform operations comprising:
- identifying a first plurality of media object characteristics associated with a first media object to be presented by a media player device, the first media object including audio data, and the first plurality of media object characteristics including a mood characteristic of the audio data;
- determining a congruency between the first plurality of media object characteristics and a second plurality of media object characteristics associated with a second media object that includes video data, the determining of the congruency including accessing a score representative of a degree of congruency between one of the first plurality of media object characteristics and one of the second plurality of media object characteristics, the score being accessed from a correlation matrix, the determining of the congruency being based on the score and a threshold value;
- determining a plurality of temporal segments of the audio data based on the mood characteristic;
- determining a duration of a temporal segment of the plurality of temporal segments of the audio data;
- identifying the second media object from a plurality of reference media objects based on the congruency between the first plurality of media object characteristics and the second plurality of media object characteristics, the identifying of the second media object being further based on the duration of the temporal segment of the audio data;
- and
- generating an audio-visual presentation to synchronously present the first media object and the second media object on the media player device.
7 more elements
A non-transitory machine-readable medium having instructions embodied thereon which, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
- identifying a first plurality of media object characteristics associated with a first media object to be presented by a media player device, the first media object including audio data, and the first plurality of media object characteristics including a mood characteristic of the audio data;
- determining a congruency between the first plurality of media object characteristics and a second plurality of media object characteristics associated with a second media object that includes video data, the determining of the congruency including accessing a score representative of a degree of congruency between one of the first plurality of media object characteristics and one of the second plurality of media object characteristics, the score being accessed from a correlation matrix, the determining of the congruency being based on the score and a threshold value;
- determining a plurality of temporal segments of the audio data based on the mood characteristic;
- determining a duration of a temporal segment of the plurality of temporal segments of the audio data;
- identifying the second media object from a plurality of reference media objects based on the congruency between the first plurality of media object characteristics and the second plurality of media object characteristics;
- and
- generating an audio-visual presentation to synchronously present the first media object and the second media object on the media player device.
4 more elements
Dependencies are inferred from the claim text.