利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

672 条记录 (耗时 0.022 秒)

    METHODS AND SYSTEMS FOR PERFORMING SIGNAL ANALYSIS TO IDENTIFY CONTENT TYPES
    2.
    发明公开
    METHODS AND SYSTEMS FOR PERFORMING SIGNAL ANALYSIS TO IDENTIFY CONTENT TYPES 审中-公开

    公开(公告)号：EP3286757A1

    公开(公告)日：2018-02-28

    申请号：EP16783868

    申请日：2016-04-21

    申请人： CYBER RESONANCE CORP

    发明人： STONE TROY CHRISTOPHER ,  LAPPI WAYNE ROY

    IPC分类号： G10L19/008 ,  G10L19/20 ,  H04S3/02

    CPC分类号： G10L25/48 ,  G06F3/165 ,  G10L19/022 ,  G10L25/03 ,  G10L25/24 ,  G10L25/87 ,  H04H60/37 ,  H04H60/58

    摘要： Systems and methods are configured to process audio signals to identify content-types. Audio content is received at an audio decoder which decodes the audio content. The decoded audio content is segmented into frames by applying a windowing function to a given audio frame using a window having a time width related to a delay time of the decoder. A power spectrum estimate of a given frame is determined. A mel filter bank is applied to the power spectrum of the frame. A DCT matrix is applied to filter bank energies to generate a DCT output. A log of the DCT output is used to generate a mel coefficient 1. A threshold for the content is dynamically determined. The mel coefficient 1 and the dynamically determined threshold are used to detect a near silence between content-types and to identify the content-types.

    Methods and apparatus to extract codes from a plurality of channels
    7.
    发明授权
    Methods and apparatus to extract codes from a plurality of channels 有权
    从多个信道提取代码的方法和设备

    公开(公告)号：EP2632176B1

    公开(公告)日：2017-05-24

    申请号：EP13002707.1

    申请日：2003-10-07

    申请人： The Nielsen Company (US), LLC

    发明人： Wright, David, H. ,  Nelson, Daniel ,  Schwerer, Ronald G.

    IPC分类号： H04R5/00 ,  G06F17/00 ,  G10L19/00 ,  H04H20/31

    CPC分类号： H04H20/31 ,  G10L19/018 ,  H04H20/89 ,  H04H60/37 ,  H04H60/58 ,  H04H2201/50

    摘要： Methods and apparatus to extract audio codes are disclosed. An example method includes receiving signals on a plurality of channels (101-104) and ranking the signals based on at least one characteristic of the signals via a signal ranker (108). A first channel from the plurality of channels is selected based upon the ranking of the signals via a channel selector (110). The example method further include determining whether a first signal on the first channel includes at least one code and extracting the at least one code from the first signal when the first signal includes the at least one code.

    摘要翻译： 公开了提取音频代码的方法和设备。 示例方法包括在多个信道（101-104）上接收信号，并且经由信号分级器（108）基于信号的至少一个特性对信号进行分级。 基于经由信道选择器（110）对信号的排序来选择来自多个信道的第一信道。 示例方法还包括确定第一信道上的第一信号是否包括至少一个代码，并且当第一信号包括至少一个代码时，从第一信号中提取至少一个代码。

    A SYSTEM AND METHOD FOR DERIVING TIMELINE METADATA FOR VIDEO CONTENT
    8.
    发明公开
    A SYSTEM AND METHOD FOR DERIVING TIMELINE METADATA FOR VIDEO CONTENT 审中-公开
    系统VERFAHREN ZUR ABLEITUNG VON ZEITLEISTENMETADATENFÜRVIDEOINHALTE

    公开(公告)号：EP3108661A2

    公开(公告)日：2016-12-28

    申请号：EP15714280.3

    申请日：2015-02-19

    申请人： Cisco Technology, Inc.

    发明人： RAI, Pete ,  RICHARDSON, David

    IPC分类号： H04N21/44 ,  H04H60/56 ,  G06F17/30

    CPC分类号： H04N21/23418 ,  H04H60/37 ,  H04H60/56 ,  H04N21/26603 ,  H04N21/84

    摘要： In one embodiment, a method implemented on a computing device for deriving timeline metadata for video content includes: capturing timeline elements through analysis of at least one of audio, visual or language aspects of the video content, interpreting the timeline elements according to associated inferences as indicative of timeline states, evaluating combinations of the timeline states according to a set of rules to derive timeline metadata, where the timeline metadata is associated with at least a portion of the video content.

    摘要翻译： 在一个实施例中，在计算设备上实现的用于导出用于视频内容的时间轴元数据的方法包括：通过分析视频内容的音频，视觉或语言方面中的至少一个来捕获时间轴元素，根据相关联的推论将时间轴元素解释为 指示时间线状态，根据一组规则评估时间线状态的组合以导出时间轴元数据，其中时间轴元数据与视频内容的至少一部分相关联。

    METHOD AND APPARATUS FOR IDENTIFYING AUDIO INFORMATION
    9.
    发明公开
    METHOD AND APPARATUS FOR IDENTIFYING AUDIO INFORMATION 有权
    VERFAHREN UND VORRICHTUNG ZUR IDENTIFIZIERUNG VON AUDIOINFORMATIONEN

    公开(公告)号：EP3082280A1

    公开(公告)日：2016-10-19

    申请号：EP16164556.9

    申请日：2016-04-08

    申请人： Xiaomi Inc.

    发明人： LV, Lu ,  LI, Shen ,  GUO, Tao

    IPC分类号： H04H60/33 ,  H04H60/74 ,  H04H60/37 ,  H04H60/65

    CPC分类号： G06F17/30743 ,  G06F3/165 ,  G06F17/2235 ,  H04H60/33 ,  H04H60/37 ,  H04H60/65 ,  H04H60/74 ,  H04L65/4023

    摘要： A method and apparatus for identifying audio information, which fall within the technical field of audio identification, are provided. The method for identifying audio information includes: identifying audio that is being played to obtain audio information of the audio (101); displaying links that are configured for the keywords in the audio information on an information presentation interface (102); when the links are triggered, displaying prestored information corresponding to the keywords (103). The audio information of the audio that is being played is obtained by identifying the audio, the links that are configured for the keywords in the audio information are displayed, and the prestored information corresponding to the keywords is displayed when the link is triggered.link

    摘要翻译： 提供了一种用于识别属于音频识别技术领域的音频信息的方法和装置。 用于识别音频信息的方法包括：识别正在播放的音频以获得音频的音频信息（101）; 显示为信息呈现界面（102）中的音频信息中的关键字配置的链接; 当链接被触发时，显示对应于关键字（103）的预存储信息。 通过识别音频来获得正在播放的音频的音频信息，显示为音频信息中的关键字配置的链接，并且当链接被触发时显示与关键字对应的预存信息。