Identification of audio content
    1.
    发明授权

    公开(公告)号:US11055059B2

    公开(公告)日:2021-07-06

    申请号:US16854278

    申请日:2020-04-21

    申请人: Sonos, Inc.

    摘要: An example implementation involves a playback device receiving digital data representing audio content, the digital data encoded in a first format. The playback device causes one or more speaker drivers to playback the audio content. The playback device decodes a portion of the received digital data to convert the portion of the received digital data from the first format to a second format and transmits, via a network interface to a computing device of an identification system, the decoded portion of the received digital data. The playback device receives, from via the network interface from the identification system, metadata corresponding to the audio content, and in response, causes a control device to display a graphical representation of the received metadata, wherein causing the control device to display the graphical representation comprises sending, via the network interface to the control device, the received metadata to the control device.

    Method and apparatus for determining (raw) video materials for news

    公开(公告)号:US11036996B2

    公开(公告)日:2021-06-15

    申请号:US16460319

    申请日:2019-07-02

    申请人: Baidu USA LLC

    发明人: Daming Lu Hao Tian

    摘要: The present disclosure discloses a method and apparatus for determining video material of news. The method for determining video material of news comprises: recognizing a person name in a news text; searching a video based on the person name, to obtain a to-be-selected video; extracting a key frame in the to-be-selected video; recognizing a person in the key frame to obtain identity information of the person; and determining the to-be-selected video as video material of news, in response to the identity information of the person conforming to the person name. The present disclosure improves the consistency between the video material of the news and the news text.

    METHOD AND APPARATUS FOR DETERMINING (RAW) VIDEO MATERIALS FOR NEWS

    公开(公告)号:US20210004603A1

    公开(公告)日:2021-01-07

    申请号:US16460319

    申请日:2019-07-02

    申请人: Baidu USA LLC

    发明人: Daming Lu Hao Tian

    摘要: The present disclosure discloses a method and apparatus for determining video material of news. The method for determining video material of news comprises: recognizing a person name in a news text; searching a video based on the person name, to obtain a to-be-selected video; extracting a key frame in the to-be-selected video; recognizing a person in the key frame to obtain identity information of the person; and determining the to-be-selected video as video material of news, in response to the identity information of the person conforming to the person name. The present disclosure improves the consistency between the video material of the news and the news text.

    VIDEO PLAYING METHOD AND DEVICE
    4.
    发明申请

    公开(公告)号:US20190297297A1

    公开(公告)日:2019-09-26

    申请号:US16301553

    申请日:2016-12-23

    发明人: Jing ZHANG

    摘要: Embodiments of the present application provide a method and apparatus for playing a video. The method includes: obtaining video information of each of moving objects contained in a currently played video frame image; updating a pre-created moving object pool based on the obtained video information of each of the moving objects; extracting, from the moving object pool, a size of a forefront moving object in the moving object pool and a position of the forefront moving object in the video frame image, obtaining a first sub-image containing the forefront moving object from the video frame image, and displaying the first sub-image in a first window; and sequentially obtaining second sub-images surrounding the forefront moving object from a cruising region of the video frame image, and displaying the second sub-images in a second window sequentially. Embodiments of the present application solve the problem that the video frame is too large to be easily viewed, and can also display the related information among the moving objects.

    Method and system for instructional video segments in conjunction with musical representation

    公开(公告)号:US20190139577A1

    公开(公告)日:2019-05-09

    申请号:US16139656

    申请日:2018-09-24

    申请人: Rodica Schileru

    发明人: Rodica Schileru

    摘要: Techniques to segment videos for instructions in conjunction with an exemplary musical representation are disclosed. According to one embodiment, a tag file is created to include a link to a source video and a plurality of tags. At least one of the tags is defined to correspond to a video portion of the source video to be associated with one or more notes in a music representation (e.g., music notes in a music score). The video portion is played back to show how the one or more notes are played whenever an area containing the one or more notes in the music representation is activated. The tag file is separate from the source video and video data representing the source video is never modified while video portions in the source video are segmented via the tag file to define pieces of the music representation, each containing one or more notes.