中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.028 seconds)

    CONSERVATIVELY ADAPTING A DEEP NEURAL NETWORK IN A RECOGNITION SYSTEM
    1.
    发明申请
    CONSERVATIVELY ADAPTING A DEEP NEURAL NETWORK IN A RECOGNITION SYSTEM 审中-公开
    在认知系统中保持深度适应深层神经网络

    公开(公告)号：WO2014137952A2

    公开(公告)日：2014-09-12

    申请号：PCT/US2014/020052

    申请日：2014-03-04

    Applicant: MICROSOFT CORPORATION

    Inventor： YU, Dong ,  YAO, Kaisheng ,  SU, Hang ,  LI, Gang ,  SEIDE, Frank

    IPC: G06N3/04 ,  G06N3/08

    CPC classification number: G10L15/16 ,  G06N3/0481 ,  G06N3/084 ,  G10L15/07 ,  G10L15/20

    Abstract: Various technologies described herein pertain to conservatively adapting a deep neural network (DNN) in a recognition system for a particular user or context. A DNN is employed to output a probability distribution over models of context-dependent units responsive to receipt of captured user input. The DNN is adapted for a particular user based upon the captured user input, wherein the adaption is undertaken conservatively such that a deviation between outputs of the adapted DNN and the unadapted DNN is constrained.

    Abstract translation: 本文描述的各种技术涉及在特定用户或上下文的识别系统中保守地适配深层神经网络（DNN）。 使用DNN来响应于接收到所捕获的用户输入而输出上下文相关单元的模型的概率分布。 所述DNN基于所捕获的用户输入适用于特定用户，其中所述适配被保守地进行，使得所适配的DNN和所述未适应的DNN的输出之间的偏差被约束。

    COMPUTER-IMPLEMENTED DEEP TENSOR NEURAL NETWORK
    2.
    发明申请
    COMPUTER-IMPLEMENTED DEEP TENSOR NEURAL NETWORK 审中-公开
    计算机实现深度传感器神经网络

    公开(公告)号：WO2014035738A1

    公开(公告)日：2014-03-06

    申请号：PCT/US2013/055898

    申请日：2013-08-21

    Applicant: MICROSOFT CORPORATION

    Inventor： YU, Dong ,  DENG, Li ,  SEIDE, Frank

    IPC: G06N3/02 ,  G06N3/04

    CPC classification number: G06N3/02 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/084

    Abstract: A deep tensor neural network (DTNN) is described herein, wherein the DTNN is suitable for employment in a computer-implemented recognition/classification system. Hidden layers in the DTNN comprise at least one projection layer, which includes a first subspace of hidden units and a second subspace of hidden units. The first subspace of hidden units receives a first nonlinear projection of input data to a projection layer and generates the first set of output data based at least in part thereon, and the second subspace of hidden units receives a second nonlinear projection of the input data to the projection layer and generates the second set of output data based at least in part thereon. A tensor layer, which can converted into a conventional layer of a DNN, generates the third set of output data based upon the first set of output data and the second set of output data.

    Abstract translation: 本文描述了深张量神经网络（DTNN），其中DTNN适合于在计算机实现的识别/分类系统中的使用。 DTNN中的隐藏层包括至少一个投影层，其包括隐藏单元的第一子空间和隐藏单元的第二子空间。 隐藏单元的第一子空间至少部分地将输入数据的第一非线性投影接收到投影层，并且至少部分地生成第一组输出数据，并且隐藏单元的第二子空间接收输入数据的第二非线性投影 投影层并且至少部分地基于其生成第二组输出数据。 可以转换成DNN的常规层的张量层基于第一组输出数据和第二组输出数据产生第三组输出数据。

    DISTRIBUTED INDEXING OF FILE CONTENT
    3.
    发明申请
    DISTRIBUTED INDEXING OF FILE CONTENT 审中-公开
    文件内容的分布式索引

    公开(公告)号：WO2009094594A2

    公开(公告)日：2009-07-30

    申请号：PCT/US2009/031913

    申请日：2009-01-23

    Applicant: MICROSOFT CORPORATION

    Inventor： THAMBIRATNAM, Albert J. K. ,  SEIDE, Frank

    IPC: G06F17/30 ,  G06F17/00

    CPC classification number: G06F17/30094

    Abstract: Described herein is technology for, among other things, distributed indexing of file content. Content-based indexing the file involves determining whether content-based index information for the file is available from an external source. This avoids repeating already-performed content analysis, which is time consuming and computationally intensive especially for non-text files. The content-based index information, if it is available, is received from the external source and may be stored. If the content-based index information is not available or is not complete, content-based index information for the file is generated and stored. Moreover, the generated content-based index information is shared with the external source. Once content analysis of the file is performed to generate content-based index information for the file, the content-based index information is available and sharable as needed. There is no need to repeat the same content analysis on the file.

    Abstract translation: 这里描述的是用于除其他之外的文件内容的分布式索引的技术。 基于内容的索引文件涉及确定文件的基于内容的索引信息是否可从外部源获得。 这避免了重复已经执行的内容分析，这非常耗时且计算密集，特别是对于非文本文件。 基于内容的索引信息（如果可用的话）从外部源接收并且可以被存储。 如果基于内容的索引信息不可用或不完整，则生成并存储用于该文件的基于内容的索引信息。 而且，生成的基于内容的索引信息与外部源共享。 一旦执行文件的内容分析以生成文件的基于内容的索引信息，则基于内容的索引信息可用且可按需共享。 没有必要对文件重复相同的内容分析。

    PERSONALIZED USER SPECIFIC GRAMMARS
    4.
    发明申请
    PERSONALIZED USER SPECIFIC GRAMMARS 审中-公开
    个性化用户特定格式

    公开(公告)号：WO2007079251A1

    公开(公告)日：2007-07-12

    申请号：PCT/US2006/049644

    申请日：2006-12-29

    Applicant: MICROSOFT CORPORATION

    Inventor： HOWELL, David, A. ,  SUNDARARAMAN, Sridhar ,  FONG, David, T. ,  SEIDE, Frank

    IPC: G06Q10/00 ,  G06F17/00

    CPC classification number: H04M3/5307 ,  H04M2201/405 ,  H04M2201/60 ,  H04M2203/253 ,  H04M2203/4509

    Abstract: Improved systems and methods are provided for transcribing audio files of voice mails sent over a unified messaging system. Customized grammars specific to a voice mail recipient are created and utilized to transcribe a received voice mail by comparing the audio file to commonly utilized words, names, acronyms, and phrases used by the recipient. Key elements are identified from the resulting text transcription to aid the recipient in processing received voice mails based on the significant content contained in the voice mail.

    Abstract translation: 提供了改进的系统和方法，用于转录通过统一消息系统发送的语音邮件的音频文件。 创建专门用于语音邮件收件人的定制语法，并将其用于通过将音频文件与通常使用的单词，姓名，首字母缩略词和短语使用的短语进行比较来转录接收到的语音邮件。 从所得到的文本转录中识别关键要素，以帮助接收者基于语音邮件中包含的重要内容来处理接收到的语音邮件。

    DISTRIBUTED INDEXING OF FILE CONTENT
    5.
    发明公开
    DISTRIBUTED INDEXING OF FILE CONTENT 审中-公开
    文件内容的分布式索引

    公开(公告)号：EP2235651A2

    公开(公告)日：2010-10-06

    申请号：EP09704564.5

    申请日：2009-01-23

    Applicant: Microsoft Corporation

    Inventor： THAMBIRATNAM, Albert J. K. ,  SEIDE, Frank

    IPC: G06F17/30 ,  G06F17/00

    CPC classification number: G06F17/30094

    Abstract: Described herein is technology for, among other things, distributed indexing of file content. Content-based indexing the file involves determining whether content-based index information for the file is available from an external source. This avoids repeating already-performed content analysis, which is time consuming and computationally intensive especially for non-text files. The content-based index information, if it is available, is received from the external source and may be stored. If the content-based index information is not available or is not complete, content-based index information for the file is generated and stored. Moreover, the generated content-based index information is shared with the external source. Once content analysis of the file is performed to generate content-based index information for the file, the content-based index information is available and sharable as needed. There is no need to repeat the same content analysis on the file.

Patent Agency Ranking