公开(公告)号：US11989231B2

公开(公告)日：2024-05-21

申请号：US17389209

申请日：2021-07-29

申请人： SONY GROUP CORPORATION

发明人： Om Prakash Chinta ,  Karthik Gayakwad ,  Shehnaz Mohamed ,  Karan Parikh

IPC分类号： G06F16/683 ,  G06F16/635 ,  G06F16/68 ,  G06F16/783

CPC分类号： G06F16/685 ,  G06F16/635 ,  G06F16/686 ,  G06F16/7834 ,  G06F16/7837

摘要： An electronic device and method for audio recommendation and generation are disclosed. The electronic device receives textual information that indicates a plurality of scenes for video content, and determines a first plurality of features for the plurality of scenes. The electronic device determines a set of positions in the textual information based on the determined first plurality of features. A set of audio files are to be inserted at the set of positions related to a set of scenes of the plurality of scenes. The electronic device determines, by an artificial intelligent (AI) engine, the set of audio files for the set of scenes, based on a second plurality of features and the first plurality of features related to the set of scenes. The electronic device controls a display device to display first information corresponding to the set of positions and second information corresponding to the set of audio files.

公开(公告)号：US12100416B2

公开(公告)日：2024-09-24

申请号：US17370138

申请日：2021-07-08

申请人： SONY GROUP CORPORATION

发明人： Kiran Charantimath ,  Karan Parikh

IPC分类号： G10L25/57 ,  G06F3/16 ,  G06F16/64 ,  G06F18/21 ,  G06F40/30 ,  G06T7/20 ,  G06T7/70 ,  G06V20/40 ,  G10L25/30 ,  G10L25/54

CPC分类号： G10L25/57 ,  G06F3/165 ,  G06F16/64 ,  G06F18/21 ,  G06F40/30 ,  G06T7/20 ,  G06T7/70 ,  G06V20/41 ,  G10L25/30 ,  G10L25/54 ,  G06T2207/10016

摘要： An electronic device and method for recommendation of audio based on video analysis is provided. The electronic device receives one or more frames of a first scene of a plurality of scenes of a video. The first scene includes a set of objects. The electronic device applies a trained neural network model on the received one or more frames to detect the set of objects. The electronic device determines an impact score of each object of the detected set of objects of the first scene based on the application of the trained neural network model on the set of objects. The electronic device further selects at least one first object from the set of objects based on the impact score of each object, and recommends one or more first audio tracks as a sound effect for the first scene based on the selected at least one first object.