Systems and methods for processing indicia for document narration
    5.
    发明授权
    Systems and methods for processing indicia for document narration 有权
    处理文件叙述标记的系统和方法

    公开(公告)号:US08352269B2

    公开(公告)日:2013-01-08

    申请号:US12687208

    申请日:2010-01-14

    IPC分类号: G10L15/00

    CPC分类号: G10L13/043 G10L13/00

    摘要: Disclosed are techniques and systems to provide a narration of a text in multiple different voices. Further disclosed are techniques and systems for processing indicia in a document to determine a portion of words and associating a particular a voice model with the portion of words based on the indicia. During a readback process, an audible output corresponding to the words in the portion of words is generated using the voice model associated with the portion of words.

    摘要翻译: 公开了提供多种不同声音中的文本的叙述的技术和系统。 还公开了用于处理文档中的标记以确定词的一部分并且将特定语音模型与基于标记的单词部分相关联的技术和系统。 在回读过程中,使用与单词部分相关联的语音模型生成对应于单词部分中的单词的可听输出。

    Device and method to assist user in conducting a transaction with a machine
    7.
    发明授权
    Device and method to assist user in conducting a transaction with a machine 有权
    帮助用户与机器进行交易的设备和方法

    公开(公告)号:US08186581B2

    公开(公告)日:2012-05-29

    申请号:US12652104

    申请日:2010-01-05

    IPC分类号: G06K5/00

    摘要: A device for assisting a user to perform a transaction on a machine is described. The device receives data that specifies a transaction mode to use for processing an image and accesses a knowledge base to provide data to configure the device for the transaction mode, the data including data specific to the transaction mode. The device receives an image or images of a portion of a machine that the user will use to perform the transaction and processes the image or images to identify a pattern of controls on the machine and to detect the presence of a user-controlled pointing item over controls on the machine. The device announces to the user the name or function of the control closest to an end of the user-controlled pointing item.

    摘要翻译: 描述用于辅助用户在机器上执行交易的设备。 设备接收指定用于处理图像的事务模式的数据,并访问知识库以提供数据以配置用于事务模式的设备,该数据包括特定于事务模式的数据。 设备接收用户将用于执行交易的机器的一部分的图像或图像,并处理图像或图像以识别机器上的控制模式并检测用户控制的指示物体的存在 控制机器。 该设备向用户通知最接近用户控制的指向项的结尾的控件的名称或功能。

    Text Stitching From Multiple Images
    8.
    发明申请
    Text Stitching From Multiple Images 有权
    文本从多个图像拼接

    公开(公告)号:US20110066424A1

    公开(公告)日:2011-03-17

    申请号:US12951254

    申请日:2010-11-22

    IPC分类号: G06F17/27 G10L13/08

    摘要: A reading machine has processing for detecting common text between a pair of individual images. The reading machine combines the text from the pair of images into a file or data structure if common text is detected, and determines if incomplete text phrases are present in the common text. If incomplete text phrases are present, the machine signals a user to move an image input device in a direction to capture more of the text.

    摘要翻译: 读取机具有用于检测一对单独图像之间的公共文本的处理。 如果检测到普通文本,阅读机将文本从一对图像组合到一个文件或数据结构中,并确定通用文本中是否存在不完整的文本短语。 如果存在不完整的文本短语,则机器向用户发送图像输入设备的方向,以捕获更多的文本。