Back to results
US 9,633,111 B1Granted
Automatic selection of representative media clips
AssigneeGoogle Inc.
InventorVictor Bennett
Life of this patent
Estimating the term…
Abstract
A system determines human recognizable labels for portions of an electronic media stream, gathers data associated with the electronic media stream from a number of media players, and determines at least one section of the electronic media stream with a particular media feature. The system selects a representative clip for the electronic media stream based on information regarding the labeled portions, the gathered data, and the at least one section.
Claims27
A method, comprising:
- receiving, by a computing device, an audio stream;
- determining labels associated with portions of the audio stream;
- gathering data of user interaction with a plurality of audio players, wherein the user interaction occurs during playback of the audio stream using the plurality of audio players, wherein the user interaction is associated with parts of the audio stream;
- analyzing one or more audio features of the audio stream to determine at least one section of the audio stream with a particular audio feature;
- generating scores for the determined labels associated with the portions, scores for the user interaction associated with the parts, and at least one score for the at least one section of the audio stream with the particular audio feature;
- and
- selecting a representative clip for the audio stream based on a combination of the scores for determined labels associated with the portions, the scores for the user interaction associated with the parts, and the at least one score for the at least one section.
4 more elements
A system, comprising:
- a memory;
- and
- a processing device, coupled to the memory, to:
- receive an audio stream;
- determine labels associated with portions of the audio stream;
- gather data of user interaction with a plurality of audio players, wherein the user interaction occurs during playback of the audio stream using the plurality of audio players, wherein the user interaction is associated with parts of the audio stream;
- analyze one or more audio features of the audio stream to determine at least one section of the audio stream with a particular audio feature;
- generate scores for the determined labels associated with the portions, scores for the user interaction associated with the parts, and at least one score for the at least one section of the audio stream with the particular audio feature;
- and
- select a representative clip for the audio stream based on a combination of the scores for determined labels associated with the portions, the scores for the user interaction associated with the parts, and the at least one score for the at least one section.
7 more elements
A method, comprising:
- determining, by a computing device, labels associated with portions of a media stream;
- collecting information of user interaction with a plurality of media players, wherein the user interaction occurs during playback of the media stream using the plurality of media players, wherein the user interaction is associated with parts of the media stream;
- generating scores for the determined labels associated with the portions and scores for the user interaction associated with the parts;
- and
- identifying a representative clip for the media stream based on a combination of the scores for the determined labels associated with the portions and the scores for the user interaction with the parts.
2 more elements
A system, comprising:
- a memory;
- and
- a processing device, coupled to the memory, to:
- determine labels associated with portions of a media stream,
- collect data of user interaction with a plurality of media players, wherein the user interaction occurs during playback of the media stream using the plurality of media players, wherein the user interaction is associated with parts of the media stream;
- generate scores for the determined labels associated with the portions and scores for the user interaction associated with the parts;
- and
- select a representative clip for the media stream based on a combination of the scores for determined labels associated with the portions and the scores for the user interaction associated with the parts.
5 more elements
Dependencies are inferred from the claim text.