中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.026 seconds)

    MULTILINGUAL DEEP NEURAL NETWORK
    1.
    发明申请
    MULTILINGUAL DEEP NEURAL NETWORK 审中-公开
    多层神经网络

    公开(公告)号：WO2014164080A1

    公开(公告)日：2014-10-09

    申请号：PCT/US2014/020448

    申请日：2014-03-05

    Applicant: MICROSOFT CORPORATION

    Inventor： HUANG, Jui-Ting ,  LI, Jinyu ,  YU, Dong ,  DENG, Li ,  GONG, Yifan

    IPC: G10L15/16

    CPC classification number: G10L15/063 ,  G06N3/0454 ,  G06N3/084 ,  G10L15/16

    Abstract: Described herein are various technologies pertaining to a multilingual deep neural network (MDNN). The MDNN includes a plurality of hidden layers, wherein values for weight parameters of the plurality of hidden layers are learned during a training phase based upon training data in terms of acoustic raw features for multiple languages. The MDNN further includes softmax layers that are trained for each target language separately, making use of the hidden layer values trained jointly with multiple source languages. The MDNN is adaptable, such that a new softmax layer may be added on top of the existing hidden layers, where the new softmax layer corresponds to a new target language.

    Abstract translation: 这里描述的是涉及多语言深层神经网络（MDNN）的各种技术。 MDNN包括多个隐藏层，其中基于针对多种语言的声学原始特征的训练数据，在训练阶段期间学习多个隐藏层的权重参数的值。 MDNN还包括针对每种目标语言分别训练的softmax层，利用与多种源语言联合训练的隐藏层值。 MDNN是适应性的，使得可以在现有隐藏层之上添加新的softmax层，其中新的softmax层对应于新的目标语言。

    LEARNING STUDENT DNN VIA OUTPUT DISTRIBUTION
    2.
    发明申请
    LEARNING STUDENT DNN VIA OUTPUT DISTRIBUTION 审中-公开
    学习DNN通过输出分配

    公开(公告)号：WO2016037350A1

    公开(公告)日：2016-03-17

    申请号：PCT/CN2014/086397

    申请日：2014-09-12

    Applicant: MICROSOFT CORPORATION ,  ZHAO, Rui ,  HUANG, Jui-Ting ,  LI, Jinyu ,  GONG, Yifan

    Inventor： ZHAO, Rui ,  HUANG, Jui-Ting ,  LI, Jinyu ,  GONG, Yifan

    IPC: G06K9/66

    CPC classification number: G06N3/084 ,  G06N3/0454 ,  G06N7/005 ,  G06N99/005 ,  G09B5/00

    Abstract: Systems and methods are provided for generating a DNN classifier by "learning" a "student" DNN model from a larger, more accurate "teacher" DNN model. The student DNN may be trained from unlabeled training data by passing the unlabeled training data through the teacher DNN, which may be trained from labeled data. In one embodiment, an iterative processis applied to train the student DNN by minimizing the divergence of the output distributions from the teacher and student DNN models. For each iteration until convergence, the difference in the outputs of these two DNNsis used to update the student DNN model, and outputs are determined again, using the unlabeled training data. The resulting trained student DNN model may be suitable for providing accurate signal processing applications on devices having limited computational or storage resources such as mobile or wearable devices. In an embodiment, the teacher DNN model comprises an ensemble of DNN models.

    Abstract translation: 提供了通过从更大，更准确的“教师”DNN模型学习“学生”DNN模型来生成DNN分类器的系统和方法。 通过传递未标记的训练数据通过教师DNN，可以从未标记的训练数据训练学生DNN，该DNN可以从标记数据中训练。 在一个实施例中，迭代过程被应用于通过最小化来自教师和学生DNN模型的输出分布的差异来训练学生DNN。 对于每次迭代直到收敛，这两个DNNsis的输出的差异用于更新学生DNN模型，并且使用未标记的训练数据再次确定输出。 所得到的训练有素的学生DNN模型可能适合于在具有有限计算或存储资源的设备（例如移动或可穿戴设备）上提供精确的信号处理应用。 在一个实施例中，教师DNN模型包括DNN模型的集合。

    MANAGED BIOMETRIC IDENTITY
    3.
    发明申请
    MANAGED BIOMETRIC IDENTITY 审中-公开
    管理生物识别

    公开(公告)号：WO2014127078A1

    公开(公告)日：2014-08-21

    申请号：PCT/US2014/016156

    申请日：2014-02-13

    Applicant: MICROSOFT CORPORATION

    Inventor： FORBES, Ronald ,  DEDHIA, Bhaven ,  KEOSABABIAN, Tim ,  LEYVAND, Tommer ,  LI, Jinyu ,  GERKEN, Timothy

    IPC: G06F21/32

    CPC classification number: G06F21/32 ,  G06F21/00

    Abstract: A computing system such as a game console maintains and updates a biometric profile of a user. In one aspect, biometric data of the user is continuously obtained from a sensor such as an infrared and visible light camera, and used to update the biometric profile using a machine learning process. In another aspect, a user is prompted to confirm his or her identify when multiple users are detected at the same time and/or when the user is detected with a confidence level which is below a threshold. A real-time image of the user being identified can be displayed on a user interface with user images associated with one or more accounts. In another aspect, the biometric profile is managed by a shell on the computing system, where the shell makes the biometric profile available to any of a number of applications on the computing system.

    Abstract translation: 诸如游戏机的计算系统维护和更新用户的生物特征。 在一个方面，从诸如红外和可见光相机的传感器连续地获得用户的生物特征数据，并且使用机器学习过程来更新生物特征。 在另一方面，当用户在同一时间检测到多个用户时和/或当以低于阈值的置信水平检测到用户时，提示用户确认他或她的身份。 被识别的用户的实时图像可以在与一个或多个帐户相关联的用户图像的用户界面上显示。 在另一方面，生物特征描述文件由计算系统上的壳体管理，其中壳体使计算系统上的任何一个应用程序可以使用生物特征。

    POSTERIOR-BASED FEATURE WITH PARTIAL DISTANCE ELIMINATION FOR SPEECH RECOGNITION
    5.
    发明申请
    POSTERIOR-BASED FEATURE WITH PARTIAL DISTANCE ELIMINATION FOR SPEECH RECOGNITION 审中-公开
    具有基于语音识别的局部距离消除的基于特征的特征

    公开(公告)号：WO2014137760A2

    公开(公告)日：2014-09-12

    申请号：PCT/US2014/019147

    申请日：2014-02-27

    Applicant: MICROSOFT CORPORATION

    Inventor： LI, Jinyu ,  YAN, Zhijie ,  HUO, Qiang ,  GONG, Yifan

    IPC: G10L15/22

    CPC classification number: G10L15/14 ,  G10L15/10

    Abstract: A high-dimensional posterior-based feature with partial distance elimination may be utilized for speech recognition. The log likelihood values of a large number of Gaussians are needed to generate the high-dimensional posterior feature. Gaussians with very small log likelihoods are associated with zero posterior values. Log likelihoods for Gaussians for a speech frame may be evaluated with a partial distance elimination method. If the partial distance of a Gaussian is already too small, the Gaussian will have a zero posterior value. The partial distance may be calculated by sequentially adding individual dimensions in a group of dimensions. The partial distance elimination occurs when less than all of the dimensions in the group are sequentially added.

    Abstract translation: 具有部分距离消除的高维后验特征可用于语音识别。 需要大量高斯的对数似然值来产生高维后验特征。 具有非常小的对数似然性的高斯与零后验值相关联。 用于语音帧的高斯的对数可能性可以用部分距离消除方法来评估。 如果高斯的部分距离已经太小，则高斯将具有零后验值。 可以通过在一组维度中依次添加个体维度来计算部分距离。 当小于组中的所有维度被顺序地添加时，发生部分距离消除。

    ILLUMINATION SENSITIVE FACE RECOGNITION
    6.
    发明申请
    ILLUMINATION SENSITIVE FACE RECOGNITION 审中-公开
    照明敏感面部识别

    公开(公告)号：WO2014059201A1

    公开(公告)日：2014-04-17

    申请号：PCT/US2013/064420

    申请日：2013-10-11

    Applicant: MICROSOFT CORPORATION

    Inventor： KRUPKA, Eyal ,  LEYVAND, Tommer ,  KVIATKOVSKY, Igor ,  ABRAMOVSKI, Igor ,  KEOSABABIAN, Tim ,  LI, Jinyu

    IPC: G06K9/00 ,  G06K9/46

    CPC classification number: G06K9/00228 ,  G06K9/4661 ,  G06T5/002

    Abstract: Methods for face recognition are provided. In one example, a method for face recognition includes receiving a user image and detecting a user luminance of data representing the user's face. An adaptive low pass filter is selected that corresponds to the user luminance of the user's face. The filter is applied to the user image to create a filtered user image. The filtered user image is projected to create a filtered user image representation. A filtered reference image representation that has been filtered with the same low pass filter is selected from a reference image database. The method then determines whether the filtered reference image representation matches the filtered user image representation.

    Abstract translation: 提供面部识别方法。 在一个示例中，一种用于人脸识别的方法包括：接收用户图像并检测表示用户脸部的数据的用户亮度。 选择对应于用户脸部的用户亮度的自适应低通滤波器。 过滤器应用于用户图像以创建过滤的用户图像。 投影过滤的用户图像以创建过滤的用户图像表示。 从参考图像数据库中选择已经用相同的低通滤波器滤波的滤波的参考图像表示。 该方法然后确定滤波的参考图像表示是否与滤波的用户图像表示匹配。

    SINGLE-PASS BOUNDING BOX CALCULATION
    7.
    发明申请
    SINGLE-PASS BOUNDING BOX CALCULATION 审中-公开

    公开(公告)号：WO2010088029A3

    公开(公告)日：2010-08-05

    申请号：PCT/US2010/020782

    申请日：2010-01-12

    Applicant: MICROSOFT CORPORATION

    Inventor： TONG, Xin ,  LI, Chen ,  LI, Jinyu

    IPC: G06T17/10

    Abstract: Embodiments for single-pass bounding box calculation are disclosed. In accordance with one embodiment, the single-pass bounding box calculation includes rendering a first target to a 2-dimensional screen space, whereby the first target includes at least six pixels. The calculation further includes producing transformed vertices in a set of geometry primitives based on an application-specified transformation. The calculation also includes generating six new points for each transformed vertex in the set of geometry primitives. The calculation additionally includes producing an initial third coordinate value for each pixel by rendering the at least six new points generate for each pixel to each corresponding pixel. The calculation further includes producing a post-rasterization value for each pixel by rasterizing the at least six new points rendered to each pixel with each corresponding pixel. Finally, the calculation includes computing bounding box information for the set of geometry primitives based on the produced third coordinate values.

Patent Agency Ranking