利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

28 条记录 (耗时 0.025 秒)

    Authoring System for IPTV Network
    21.
    发明申请
    Authoring System for IPTV Network 有权
    IPTV网络创作系统

    公开(公告)号：US20140229973A1

    公开(公告)日：2014-08-14

    申请号：US14253527

    申请日：2014-04-15

    申请人： AT&T Intellectual Property I, LP

    发明人： Hisao Chang ,  Javier Arellano

    IPC分类号： H04N21/8549 ,  H04N21/435 ,  G10L15/26 ,  H04N9/79 ,  H04N21/472 ,  H04N21/61 ,  H04N7/167 ,  G11B27/034

    CPC分类号： H04N21/8549 ,  G10L15/26 ,  G11B27/034 ,  H04N7/1675 ,  H04N9/79 ,  H04N21/40 ,  H04N21/435 ,  H04N21/47205 ,  H04N21/6125 ,  H04N21/64322

    摘要： In an embodiment, a system and method permit an IPTV subscriber to display on a channel of an IPTV network video data from a subscriber video database. The system may include, in addition to the IPTV network and the subscriber database, an IPTV server and an IPTV set top box. The IPTV set top box is configured to receive commands causing the IPTV set top box to retrieve video data from an IPTV subscriber database, display the video data on an IPTV display unit; and to transmit the video data over an IPTV network to an IPTV server. The IPTV server is configured to transmit the video data from the IPTV server over the IPTV network such that the video data is displayable on a channel of the IPTV network.

    摘要翻译： 在一个实施例中，系统和方法允许IPTV订户在来自用户视频数据库的IPTV网络视频数据的频道上显示。 除了IPTV网络和用户数据库之外，该系统还可以包括IPTV服务器和IPTV机顶盒。 IPTV机顶盒被配置为接收导致IPTV机顶盒从IPTV订户数据库检索视频数据的命令，在IPTV显示单元上显示视频数据; 并通过IPTV网络将视频数据发送到IPTV服务器。 IPTV服务器被配置为通过IPTV网络从IPTV服务器发送视频数据，使得视频数据可以在IPTV网络的信道上显示。

    Method and apparatus to generate a speech recognition library
    23.
    发明授权
    Method and apparatus to generate a speech recognition library 有权
    生成语音识别库的方法和装置

    公开(公告)号：US09536519B2

    公开(公告)日：2017-01-03

    申请号：US14926544

    申请日：2015-10-29

    申请人： AT&T INTELLECTUAL PROPERTY I, LP

    发明人： Hisao Chang

    IPC分类号： G10L15/26 ,  G10L15/06 ,  G06F17/27 ,  G10L13/04 ,  G10L13/06 ,  G10L15/187 ,  G10L25/57 ,  G10L13/02 ,  G06F17/21 ,  G10L13/08

    CPC分类号： G10L15/063 ,  G06F17/21 ,  G06F17/27 ,  G10L13/02 ,  G10L13/04 ,  G10L13/06 ,  G10L13/08 ,  G10L15/06 ,  G10L15/187 ,  G10L15/26 ,  G10L25/57 ,  G10L2015/025

    摘要： Methods and apparatus to generate a speech recognition library for use by a speech recognition system are disclosed. An example method comprises identifying a plurality of video segments having closed caption data corresponding to a phrase, the plurality of video segments associated with respective ones of a plurality of audio data segments, computing a plurality of difference metrics between a baseline audio data segment associated with the phrase and respective ones of the plurality of audio data segments, selecting a set of the plurality of audio data segments based on the plurality of difference metrics, identifying a first one of the audio data segments in the set as a representative audio data segment, determining a first phonetic transcription of the representative audio data segment, and adding the first phonetic transcription to a speech recognition library when the first phonetic transcription differs from a second phonetic transcription associated with the phrase in the speech recognition library.

    摘要翻译： 公开了一种用于生成语音识别库供语音识别系统使用的方法和装置。 一个示例性方法包括识别具有与短语相对应的隐藏字幕数据的多个视频片段，所述多个视频片段与多个音频数据片段中的相应音频数据片段相关联，计算与相关联的基线音频数据片段之间的多个差异度量 所述短语和所述多个音频数据段中的相应的音频数据段，基于所述多个差分度量来选择所述多个音频数据段的集合，将所述组中的所述音频数据段中的第一个识别为代表性音频数据段， 确定代表性音频数据段的第一语音转录，并且当第一语音转录与语音识别库中的短语相关联的第二语音转录不同时，将第一语音转录添加到语音识别库。

    METHOD AND APPARATUS TO GENERATE A SPEECH RECOGNITION LIBRARY
    26.
    发明申请
    METHOD AND APPARATUS TO GENERATE A SPEECH RECOGNITION LIBRARY 有权
    生成语音识别库的方法和装置

    公开(公告)号：US20160049146A1

    公开(公告)日：2016-02-18

    申请号：US14926544

    申请日：2015-10-29

    申请人： AT&T INTELLECTUAL PROPERTY I, LP

    发明人： Hisao Chang

    IPC分类号： G10L15/06 ,  G10L25/57 ,  G10L15/26 ,  G06F17/27 ,  G10L15/187

    CPC分类号： G10L15/063 ,  G06F17/21 ,  G06F17/27 ,  G10L13/02 ,  G10L13/04 ,  G10L13/06 ,  G10L13/08 ,  G10L15/06 ,  G10L15/187 ,  G10L15/26 ,  G10L25/57 ,  G10L2015/025

    摘要： Methods and apparatus to generate a speech recognition library for use by a speech recognition system are disclosed. An example method comprises identifying a plurality of video segments having closed caption data corresponding to a phrase, the plurality of video segments associated with respective ones of a plurality of audio data segments, computing a plurality of difference metrics between a baseline audio data segment associated with the phrase and respective ones of the plurality of audio data segments, selecting a set of the plurality of audio data segments based on the plurality of difference metrics, identifying a first one of the audio data segments in the set as a representative audio data segment, determining a first phonetic transcription of the representative audio data segment, and adding the first phonetic transcription to a speech recognition library when the first phonetic transcription differs from a second phonetic transcription associated with the phrase in the speech recognition library.

    摘要翻译： 公开了一种用于生成语音识别库供语音识别系统使用的方法和装置。 一个示例性方法包括识别具有与短语相对应的隐藏字幕数据的多个视频片段，所述多个视频片段与多个音频数据片段中的相应音频数据片段相关联，计算与相关联的基线音频数据片段之间的多个差异度量 所述短语和所述多个音频数据段中的相应的音频数据段，基于所述多个差分度量来选择所述多个音频数据段的集合，将所述组中的所述音频数据段中的第一个识别为代表性音频数据段， 确定代表性音频数据段的第一语音转录，并且当第一语音转录与语音识别库中的短语相关联的第二语音转录不同时，将第一语音转录添加到语音识别库。

    Voice Enabled Remote Control for a Set-Top Box
    27.
    发明申请
    Voice Enabled Remote Control for a Set-Top Box 有权

    公开(公告)号：US20150339916A1

    公开(公告)日：2015-11-26

    申请号：US14819613

    申请日：2015-08-06

    申请人： AT&T INTELLECTUAL PROPERTY I, LP

    发明人： Hisao Chang ,  Iker Arizmendi

    IPC分类号： G08C17/00 ,  G10L15/00

    CPC分类号： G08C17/00 ,  G08C2201/31 ,  G10L15/00 ,  G10L15/26

    摘要： A remote control device includes a digital audio storage device, a talk button, and an optical distance measurer. The digital audio storage device is configured to continually record an audio input for a specific amount of time. The talk button is coupled to the digital audio storage device and is configured to initiate a transmission of the audio input to a set-top box device. The optical distance measurer is coupled to the talk button and is configured to automatically measure a distance to a user in response to the talk button being pressed.

    APPARATUS AND METHOD FOR PROVIDING MESSAGES IN A SOCIAL NETWORK
    28.
    发明申请
    APPARATUS AND METHOD FOR PROVIDING MESSAGES IN A SOCIAL NETWORK 有权
    在社交网络中提供信息的装置和方法

    公开(公告)号：US20140229176A1

    公开(公告)日：2014-08-14

    申请号：US14256549

    申请日：2014-04-18

    申请人： AT&T Intellectual Property I, LP

    发明人： Hisao Chang ,  Bernard S. Renger

    IPC分类号： G10L15/26 ,  G09G5/377 ,  G06F3/0481

    CPC分类号： H04L51/32 ,  G06F3/0481 ,  G09G5/377 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  G10L17/00 ,  H04L12/1813 ,  H04L51/10 ,  H04L67/306 ,  H04M3/4936 ,  H04M2201/40 ,  H04M2201/60

    摘要： A system that incorporates teachings of the present disclosure may include, for example, a server including a controller to receive audio signals and content identification information from a media processor, generate text representing a voice message based on the audio signals, determine an identity of media content based on the content identification information, generate an enhanced message having text and additional content where the additional content is obtained by the controller based on the identity of the media content, and transmit the enhanced message to the media processor for presentation on the display device, where the enhanced message is accessible by one or more communication devices that are associated with a social network and remote from the media processor. Other embodiments are disclosed.

    摘要翻译： 结合本公开的教导的系统可以包括例如包括控制器的服务器，所述控制器从媒体处理器接收音频信号和内容标识信息，基于音频信号生成表示语音消息的文本，确定媒体的身份 基于内容识别信息生成内容，生成具有文本和附加内容的增强消息，其中控制器基于媒体内容的身份获取附加内容，并将增强消息发送到媒体处理器以呈现在显示设备上 其中增强的消息可由与社交网络相关联且远离媒体处理器的一个或多个通信设备访问。 公开了其他实施例。