利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

30 条记录 (耗时 0.022 秒)

    Incorporation of speech engine training into interactive user tutorial
    11.
    发明申请
    Incorporation of speech engine training into interactive user tutorial 审中-公开
    将言语引擎训练纳入交互式用户教程

    公开(公告)号：US20070055520A1

    公开(公告)日：2007-03-08

    申请号：US11265726

    申请日：2005-11-02

    申请人： David Mowatt ,  Felix Andrew ,  James Jacoby ,  Oliver Scholz ,  Paul Kennedy

    发明人： David Mowatt ,  Felix Andrew ,  James Jacoby ,  Oliver Scholz ,  Paul Kennedy

    IPC分类号： G10L15/04

    CPC分类号： G10L15/22 ,  G09B5/04 ,  G10L15/063 ,  G10L2015/0631 ,  G10L2015/228

    摘要： The present invention combines speech recognition tutorial training with speech recognizer voice training. The system prompts the user for speech data and simulates, with predefined screenshots, what happens when speech commands are received. At each step in the tutorial process, when the user is prompted for an input, the system is configured such that only a predefined set (which may be one) of user inputs will be recognized by the speech recognizer. When a successful recognition is being made, the speech data is used to train the speech recognition system.

    摘要翻译： 本发明将语音识别教程训练与语音识别器语音训练相结合。 系统提示用户语音数据，并用预定义的屏幕截图模拟接收到语音命令时会发生什么。 在教程过程的每个步骤中，当用户被提示输入时，系统被配置为使得只有预定义的用户输入（可以是一个）用户输入的集合将被语音识别器识别。 当成功识别时，语音数据用于训练语音识别系统。

    Recognizing multiple semantic items from single utterance
    12.
    发明授权
    Recognizing multiple semantic items from single utterance 有权
    从单一语音识别多个语义项

    公开(公告)号：US08725492B2

    公开(公告)日：2014-05-13

    申请号：US12042460

    申请日：2008-03-05

    申请人： Julian J Odell ,  Robert L. Chambers ,  Oliver Scholz

    发明人： Julian J Odell ,  Robert L. Chambers ,  Oliver Scholz

    IPC分类号： G06F17/28

    CPC分类号： G10L15/1815

    摘要： Semantically distinct items are extracted from a single utterance by repeatedly recognizing the same utterance using constraints provided by semantic items already recognized. User feedback for selection or correction of partially recognized utterance may be used in a hierarchical, multi-modal, or single step manner. An accuracy of recognition is preserved while the less structured and more natural single utterance recognition form is allowed to be used.

    摘要翻译： 通过使用已经识别的语义项提供的约束重复地识别相同的话语，从单个话语中提取语义上不同的项目。 用于部分识别的话语的选择或校正的用户反馈可以以分层，多模式或单步的方式使用。 识别的准确性得到保留，而较少结构化和更自然的单个话语识别形式被允许使用。

    Apparatus and method for combining several sub-images for any imaging surface areas
    13.
    发明授权
    Apparatus and method for combining several sub-images for any imaging surface areas 有权
    用于组合用于任何成像表面区域的几个子图像的装置和方法

    公开(公告)号：US08275217B2

    公开(公告)日：2012-09-25

    申请号：US12438803

    申请日：2007-08-02

    申请人： Matthias Kube ,  Oliver Scholz ,  Rolf Behrendt

    发明人： Matthias Kube ,  Oliver Scholz ,  Rolf Behrendt

    IPC分类号： G06K9/32

    CPC分类号： G06T7/33 ,  G06T2207/10116 ,  G06T2207/30116

    摘要： An apparatus provides an image on the basis of a plurality of input images. The apparatus includes a first stage having at least a first and a second combiner, each of the combiners including a first storer for storing image data of the input images, a first processor for processing the image data of the input images into an intermediate image, and a second storer for storing image data of the intermediate image. The apparatus further includes a second stage having at least one further combiner, the further combiner including a third storer for storing image data of those intermediate images which are stored in the second storer of the first stage, a second processor for processing the image data from the third storer, so as to combine the image data of the intermediate images into the image, and a fourth storer for storing image data of the image.

    摘要翻译： 一种装置基于多个输入图像提供图像。 该装置包括具有至少第一和第二组合器的第一级，每个组合器包括用于存储输入图像的图像数据的第一存储器，用于将输入图像的图像数据处理成中间图像的第一处理器， 以及用于存储中间图像的图像数据的第二存储器。 所述装置还包括具有至少一个另外的组合器的第二级，所述另外的组合器包括用于存储存储在第一级的第二存储器中的那些中间图像的图像数据的第三存储器，用于处理来自 第三存储器，以便将中间图像的图像数据组合成图像;以及第四存储器，用于存储图像的图像数据。

    Apparatus and Method for Combining Several Sub-Images for any Imaging Surface Areas
    14.
    发明申请
    Apparatus and Method for Combining Several Sub-Images for any Imaging Surface Areas 有权
    用于组合任何成像表面区域的几个子图像的装置和方法

    公开(公告)号：US20100067828A1

    公开(公告)日：2010-03-18

    申请号：US12438803

    申请日：2007-08-02

    申请人： Matthias Kube ,  Oliver Scholz ,  Rolf Behrendt

    发明人： Matthias Kube ,  Oliver Scholz ,  Rolf Behrendt

    IPC分类号： G06K9/36

    CPC分类号： G06T7/33 ,  G06T2207/10116 ,  G06T2207/30116

    摘要： An apparatus provides an image on the basis of a plurality of input images. The apparatus includes a first stage having at least a first and a second combiner, each of the combiners including a first storer for storing image data of the input images, a first processor for processing the image data of the input images into an intermediate image, and a second storer for storing image data of the intermediate image. The apparatus further includes a second stage having at least one further combiner, the further combiner including a third storer for storing image data of those intermediate images which are stored in the second storer of the first stage, a second processor for processing the image data from the third storer, so as to combine the image data of the intermediate images into the image, and a fourth storer for storing image data of the image.

    摘要翻译： 一种装置基于多个输入图像提供图像。 该装置包括具有至少第一和第二组合器的第一级，每个组合器包括用于存储输入图像的图像数据的第一存储器，用于将输入图像的图像数据处理成中间图像的第一处理器， 以及用于存储中间图像的图像数据的第二存储器。 所述装置还包括具有至少一个另外的组合器的第二级，所述另外的组合器包括用于存储存储在第一级的第二存储器中的那些中间图像的图像数据的第三存储器，用于处理来自 第三存储器，以便将中间图像的图像数据组合成图像;以及第四存储器，用于存储图像的图像数据。

    APPARATUS AND METHOD FOR REDUCING TRANSITION ARTIFACTS IN AN OVERALL IMAGE COMPOSED OF SUB-IMAGES
    18.
    发明申请
    APPARATUS AND METHOD FOR REDUCING TRANSITION ARTIFACTS IN AN OVERALL IMAGE COMPOSED OF SUB-IMAGES 审中-公开
    用于减少由副图像组成的整体图像中的过渡艺术品的装置和方法

    公开(公告)号：US20090324128A1

    公开(公告)日：2009-12-31

    申请号：US12438129

    申请日：2007-08-22

    申请人： Matthias Kube ,  Oliver Scholz ,  Rolf Behrendt

    发明人： Matthias Kube ,  Oliver Scholz ,  Rolf Behrendt

    IPC分类号： G06K9/40

    CPC分类号： G06T3/4038 ,  G06T5/005 ,  G06T7/0004 ,  G06T2207/10116 ,  G06T2207/20021 ,  G06T2207/30136 ,  H04N1/387

    摘要： The present invention provides an apparatus and a method for reducing transition artifacts in an overall image composed of sub-images whose image areas have overlap areas. The apparatus includes a storer for storing image data of the pixels of the sub-images, and a generator for generating the overall image, on the basis of the image data of the sub-images by superposition of the image data of the pixels in the overlap area in accordance with a weighting, the weighting being configured such that any influence of a pixel of a sub-image which would cause an artifact in the overall image is reduced in the overall image.

    摘要翻译： 本发明提供一种用于减少由图像区域具有重叠区域的子图像构成的整体图像中的转变伪影的装置和方法。 该装置包括存储器，用于存储子图像的像素的图像数据，以及用于生成整个图像的发生器，基于子图像的图像数据，通过叠加图像数据中的像素的图像数据 重叠区域，所述加权被配置为使得在整个图像中减少整个图像中将导致伪影的子图像的像素的任何影响。

    Recognizing multiple semantic items from single utterance
    19.
    发明申请
    Recognizing multiple semantic items from single utterance 有权
    从单一语音识别多个语义项

    公开(公告)号：US20090228270A1

    公开(公告)日：2009-09-10

    申请号：US12042460

    申请日：2008-03-05

    申请人： Julian J. Odell ,  Robert L. Chambers ,  Oliver Scholz

    发明人： Julian J. Odell ,  Robert L. Chambers ,  Oliver Scholz

    IPC分类号： G10L15/00

    CPC分类号： G10L15/1815

    摘要： Semantically distinct items are extracted from a single utterance by repeatedly recognizing the same utterance using constraints provided by semantic items already recognized. User feedback for selection or correction of partially recognized utterance may be used in a hierarchical, multi-modal, or single step manner. An accuracy of recognition is preserved while the less structured and more natural single utterance recognition form is allowed to be used.

    摘要翻译： 通过使用已经识别的语义项提供的约束重复地识别相同的话语，从单个话语中提取语义上不同的项目。 用于部分识别的话语的选择或校正的用户反馈可以以分层，多模式或单步的方式使用。 识别的准确性得到保留，而较少结构化和更自然的单个话语识别形式被允许使用。

    Wireless speech recognition
    20.
    发明申请
    Wireless speech recognition 有权
    无线语音识别

    公开(公告)号：US20070219802A1

    公开(公告)日：2007-09-20

    申请号：US11378418

    申请日：2006-03-17

    申请人： Daniel Cook ,  David Mowatt ,  Oliver Scholz ,  Oscar Murillo

    发明人： Daniel Cook ,  David Mowatt ,  Oliver Scholz ,  Oscar Murillo

    IPC分类号： G10L21/00

    CPC分类号： G10L15/30 ,  Y10S707/99934 ,  Y10S707/99939

    摘要： A method of interacting with a speech recognition (SR)-enabled personal computer (PC) is provided in which a user SR profile is transferred from a wireless-enabled device to the SR-enabled PC. Interaction with SR applications, on the SR-enabled PC, is carried out by transmitting speech signals wirelessly to the SR-enabled PC. The transmitted speech signals are recognized with the help of the transferred user SR profile.

    摘要翻译： 提供了一种与启用语音识别（SR）的个人计算机（PC）进行交互的方法，其中用户SR简档从启用无线的设备传送到启用SR的PC。 在支持SR的PC上与SR应用的交互是通过无线方式将语音信号发送到支持SR的PC进行的。 所传输的语音信号在传送的用户SR简档的帮助下被识别。