利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

90 条记录 (耗时 0.032 秒)

    SYSTEMS AND METHODS FOR TWO STREAM INDEXING OF AUDIO CONTENT
    1.
    发明申请
    SYSTEMS AND METHODS FOR TWO STREAM INDEXING OF AUDIO CONTENT 有权
    用于两个音频内容的流水线索引的系统和方法

    公开(公告)号：US20120136870A1

    公开(公告)日：2012-05-31

    申请号：US12956625

    申请日：2010-11-30

    申请人： Anupam Joshi ,  Sougata Mukherjea ,  Nitendra Rajput

    发明人： Anupam Joshi ,  Sougata Mukherjea ,  Nitendra Rajput

    IPC分类号： G06F17/30 ,  G10L15/04

    CPC分类号： G10L15/26

    摘要： Systems and methods provide for indexing audio content by fusing the indexes derived from a keyword stream and a large vocabulary stream search. For example, systems and methods provide for two stream searching of Spoken Web VoiceSites, wherein metadata is extracted from the VoiceSite and is used to determine a set of keywords for high precision search while a traditional standard vocabulary set is used to perform a high results, low precision search. The results of the keyword search and the standard vocabulary search are fused together to form a comprehensive, ranked list of results.

    摘要翻译： 系统和方法通过融合从关键字流和大量词汇流搜索导出的索引来提供索引音频内容。 例如，系统和方法提供对语音Web VoiceSites的两个流搜索，其中从语音网站提取元数据，并且用于确定用于高精度搜索的一组关键字，而传统的标准词汇集被用于执行高结果， 低精度搜索。 关键词搜索和标准词汇搜索的结果融合在一起，形成一个综合排名的结果列表。

    Systems and methods for two stream indexing of audio content
    2.
    发明授权
    Systems and methods for two stream indexing of audio content 有权
    音频内容的两个流索引的系统和方法

    公开(公告)号：US08825661B2

    公开(公告)日：2014-09-02

    申请号：US12956625

    申请日：2010-11-30

    申请人： Anupam Joshi ,  Sougata Mukherjea ,  Nitendra Rajput

    发明人： Anupam Joshi ,  Sougata Mukherjea ,  Nitendra Rajput

    IPC分类号： G06F7/00 ,  G06F17/30

    CPC分类号： G10L15/26

    摘要： Systems and methods provide for indexing audio content by fusing the indexes derived from a keyword stream and a large vocabulary stream search. For example, systems and methods provide for two stream searching of Spoken Web VoiceSites, wherein metadata is extracted from the VoiceSite and is used to determine a set of keywords for high precision search while a traditional standard vocabulary set is used to perform a high results, low precision search. The results of the keyword search and the standard vocabulary search are fused together to form a comprehensive, ranked list of results.

    摘要翻译： 系统和方法通过融合从关键字流和大量词汇流搜索导出的索引来提供索引音频内容。 例如，系统和方法提供对语音Web VoiceSites的两个流搜索，其中从语音网站提取元数据，并且用于确定用于高精度搜索的一组关键字，而传统的标准词汇集被用于执行高结果， 低精度搜索。 关键词搜索和标准词汇搜索的结果融合在一起，形成一个综合排名的结果列表。

    Making user generated audio content on the spoken web navigable by community tagging
    5.
    发明授权
    Making user generated audio content on the spoken web navigable by community tagging 有权
    在通过社区标记导航的口语网络上创建用户生成的音频内容

    公开(公告)号：US09075874B2

    公开(公告)日：2015-07-07

    申请号：US13596901

    申请日：2012-08-28

    申请人： Sheetal Agarwal ,  Anupam Jain ,  Arun Kumar ,  Amit Anil Nanavati ,  Nitendra Rajput

    发明人： Sheetal Agarwal ,  Anupam Jain ,  Arun Kumar ,  Amit Anil Nanavati ,  Nitendra Rajput

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30755 ,  G06F17/3074 ,  G06F17/30775 ,  G06F17/30778 ,  G06F17/30899 ,  G06F17/30902

    摘要： Methods and arrangements for creating and building subcategories in a user-based voice application. User posts are appended to a category in a voice application and subdivision of the category is prompted upon satisfaction of a first condition. The category is designated as a parent category, and at least one subcategory nomination are solicited from users. User input is solicited on appending at least one nominated subcategory to the parent category, and a nominated subcategory is appended to the parent category upon satisfaction of a second condition. User input is solicited to reassign a user post from the parent category to at least one subcategory.

    摘要翻译： 在基于用户的语音应用程序中创建和构建子类别的方法和安排。 用户帖子被附加到语音应用中的类别，并且在满足第一条件时提示该类别的细分。 该类别被指定为父类别，并且从用户请求至少一个子类别提名。 征求用户输入，将至少一个指定子类别附加到父类别，并且在满足第二个条件时，将指定的子类别附加到父类别。 请求用户输入将用户的帖子从父类别重新分配到至少一个子类别。

    Web video occlusion: a method for rendering the videos watched over multiple windows
    6.
    发明授权
    Web video occlusion: a method for rendering the videos watched over multiple windows 有权
    网络视频遮挡：用于渲染在多个窗口上观看的视频的方法

    公开(公告)号：US09069374B2

    公开(公告)日：2015-06-30

    申请号：US13343265

    申请日：2012-01-04

    申请人： Pramod K. Sudhakar Palla ,  Nitendra Rajput

    发明人： Pramod K. Sudhakar Palla ,  Nitendra Rajput

    IPC分类号： G06F3/00 ,  G06F3/048 ,  G06F3/14 ,  G06F3/0481

    CPC分类号： G06F3/0481 ,  G06F3/00 ,  G06F3/04842 ,  G06F3/14 ,  G06F3/1423 ,  G09G5/14 ,  G09G2340/125

    摘要： Computer-implemented methods, computer program products and computer systems that render display of a video on a first page, that has been occluded from view by the subsequent viewing of a second page, to viewing on such subsequently viewed second page. Source location of the video is identified from source code of the first page, the identified video source is retrieved, and then it is input into source code of the second page to transfer the video to the second page. The video may then me displayed on the second page. The computer program products and computer systems both include a number of program instructions for effecting the transfer of the video from the first page to the second page for the continuous unobstructed or non-occluded viewing thereof.

    摘要翻译： 计算机实现的方法，计算机程序产品和计算机系统，其通过后续查看第二页面而在第一页上显示视频已被遮挡，从而在随后观看的第二页上进行观看。 从第一页的源代码识别视频的源位置，检索识别的视频源，然后将其输入到第二页的源代码以将视频传送到第二页。 然后可以在第二页显示视频。 计算机程序产品和计算机系统都包括多个程序指令，用于实现将视频从第一页传送到第二页，用于连续无障碍或不遮挡观看。

    VISUALIZING, NAVIGATING AND INTERACTING WITH AUDIO CONTENT
    8.
    发明申请
    VISUALIZING, NAVIGATING AND INTERACTING WITH AUDIO CONTENT 有权
    可视化，导航和互动音频内容

    公开(公告)号：US20130054249A1

    公开(公告)日：2013-02-28

    申请号：US13216807

    申请日：2011-08-24

    申请人： Amit Anil Nanavati ,  Nitendra Rajput

    发明人： Amit Anil Nanavati ,  Nitendra Rajput

    IPC分类号： G10L21/06

    CPC分类号： H04M3/493 ,  G10L21/06 ,  H04M3/4938 ,  H04M2203/25

    摘要： Methods and arrangements for visually representing audio content in a voice application. A display is connected to a voice application, and an image is displayed on the display, the image comprising a main portion and at least one subsidiary portion, the main portion representing a contextual entity of the audio content and the at least one subsidiary portion representing at least one participatory entity of the audio content. The at least one subsidiary portion is displayed without text, and the image is changed responsive to changes in audio content in the voice application.

    摘要翻译： 在语音应用程序中视觉表示音频内容的方法和布置。 显示器连接到语音应用，并且在显示器上显示图像，该图像包括主要部分和至少一个辅助部分，主要部分表示音频内容的上下文实体，以及至少一个辅助部分表示 音频内容的至少一个参与实体。 所述至少一个辅助部分被显示为没有文本，并且响应于语音应用中的音频内容的改变来改变图像。

    SPEAKER ADAPTATION OF VOCABULARY FOR SPEECH RECOGNITION
    9.
    发明申请
    SPEAKER ADAPTATION OF VOCABULARY FOR SPEECH RECOGNITION 有权
    语音识别词汇的适应

    公开(公告)号：US20120035928A1

    公开(公告)日：2012-02-09

    申请号：US13273020

    申请日：2011-10-13

    申请人： Nitendra Rajput ,  Ashish Verma

    发明人： Nitendra Rajput ,  Ashish Verma

    IPC分类号： G10L15/06

    CPC分类号： G10L17/02 ,  G10L15/07

    摘要： A phonetic vocabulary for a speech recognition system is adapted to a particular speaker's pronunciation. A speaker can be attributed specific pronunciation styles, which can be identified from specific pronunciation examples. Consequently, a phonetic vocabulary can be reduced in size, which can improve recognition accuracy and recognition speed.

    摘要翻译： 用于语音识别系统的语音词汇适用于特定说话者的发音。 扬声器可以归因于特定的发音风格，可以从具体的发音示例中识别。 因此，可以减小语音词汇量，从而提高识别精度和识别速度。

    User Driven Audio Content Navigation
    10.
    发明申请
    User Driven Audio Content Navigation 有权
    用户驱动的音频内容导航

    公开(公告)号：US20110320950A1

    公开(公告)日：2011-12-29

    申请号：US12822802

    申请日：2010-06-24

    申请人： Nitendra Rajput ,  Om D. Deshmukh

    发明人： Nitendra Rajput ,  Om D. Deshmukh

    IPC分类号： G06F3/16

    CPC分类号： G06F17/30775 ,  G06F17/30743 ,  G10L15/00 ,  G10L21/043 ,  H04M3/4938

    摘要： Systems and associated methods configured to provide user-driven audio content navigation for the spoken web are described. Embodiments allow users to skim audio for content that seems to be of relevance to the user, similar to visual skimming of standard web pages, and mark point of interest within the audio. Embodiments provide techniques for navigating audio content while interacting with information systems in a client-server environment, where the client device can be a simple, standard telephone.

    摘要翻译： 描述了配置成为口头网络提供用户驱动的音频内容导航的系统和相关方法。 实施例允许用户对似乎与用户相关的内容来删除音频，类似于标准网页的视觉撇除，并标记音频内的兴趣点。 实施例提供了用于在客户机 - 服务器环境中与信息系统交互的情况下导航音频内容的技术，其中客户端设备可以是简单的标准电话。