中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.019 seconds)

    DYNAMIC LANGUAGE MODEL
    1.
    发明申请
    DYNAMIC LANGUAGE MODEL 审中-公开

    公开(公告)号：US20160342682A1

    公开(公告)日：2016-11-24

    申请号：US15231066

    申请日：2016-08-08

    Applicant: Google Inc.

    Inventor： Pedro J. Moreno Mengibar ,  Michael H. Cohen

    IPC: G06F17/30 ,  G10L15/197 ,  G10L15/24 ,  G10L15/26

    CPC classification number: G06F17/30696 ,  G06F17/30241 ,  G06F17/30292 ,  G06F17/30684 ,  G06F17/30687 ,  G10L15/005 ,  G10L15/14 ,  G10L15/197 ,  G10L15/24 ,  G10L15/26 ,  G10L15/265 ,  G10L2015/0633 ,  G10L2015/081 ,  G10L2015/228

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.

    Automatic Language Model Update
    4.
    发明申请
    Automatic Language Model Update 有权

    公开(公告)号：US20160035345A1

    公开(公告)日：2016-02-04

    申请号：US14879755

    申请日：2015-10-09

    Applicant: Google Inc.

    Inventor： Michael H. Cohen ,  Shumeet Baluja ,  Pedro J. Moreno Mengibar

    IPC: G10L15/065 ,  G10L15/26 ,  G10L15/06

    CPC classification number: G10L15/065 ,  G10L15/06 ,  G10L15/063 ,  G10L15/187 ,  G10L15/26 ,  G10L2015/0635

    Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.

    Dynamic Language Model
    5.
    发明申请
    Dynamic Language Model 有权
    动态语言模型

    公开(公告)号：US20150254334A1

    公开(公告)日：2015-09-10

    申请号：US14719178

    申请日：2015-05-21

    Applicant: Google Inc.

    Inventor： Pedro J. Moreno Mengibar ,  Michael H. Cohen

    IPC: G06F17/30 ,  G10L15/14 ,  G10L15/00 ,  G10L15/26

    CPC classification number: G06F17/30696 ,  G06F17/30241 ,  G06F17/30292 ,  G06F17/30684 ,  G06F17/30687 ,  G10L15/005 ,  G10L15/14 ,  G10L15/197 ,  G10L15/24 ,  G10L15/26 ,  G10L15/265 ,  G10L2015/0633 ,  G10L2015/081 ,  G10L2015/228

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.

    Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的用于语音识别的计算机程序。 方法之一包括接收用于语音识别的基本语言模型，其包括具有基本概率值的第一字序列; 接收与查询语境相关联的语音搜索查询; 当查询上下文满足与定制语言模型相关联的一个或多个标准时，确定要使用定制语言模型; 获得定制语言模型，包括具有调整概率值的第一单词序列的定制语言模型是根据查询语境调整的基本概率值; 以及基于一个或多个概率将所述语音搜索查询转换为文本搜索查询，所述概率中的每一个对应于一个或多个单词序列的组中的单词序列，所述组包括具有调整后的概率值的第一单词序列。

    DYNAMIC LANGUAGE MODEL
    7.
    发明申请
    DYNAMIC LANGUAGE MODEL 有权

    公开(公告)号：US20160140218A1

    公开(公告)日：2016-05-19

    申请号：US15006392

    申请日：2016-01-26

    Applicant: Google Inc.

    Inventor： Pedro J. Moreno Mengibar ,  Michael H. Cohen

    IPC: G06F17/30 ,  G10L15/197 ,  G10L15/24 ,  G10L15/26

    CPC classification number: G06F17/30696 ,  G06F17/30241 ,  G06F17/30292 ,  G06F17/30684 ,  G06F17/30687 ,  G10L15/005 ,  G10L15/14 ,  G10L15/197 ,  G10L15/24 ,  G10L15/26 ,  G10L15/265 ,  G10L2015/0633 ,  G10L2015/081 ,  G10L2015/228

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.

    Dynamic language model
    10.
    发明授权
    Dynamic language model 有权
    动态语言模型

    公开(公告)号：US09043205B2

    公开(公告)日：2015-05-26

    申请号：US13802414

    申请日：2013-03-13

    Applicant: Google Inc.

    Inventor： Pedro J. Moreno Mengibar ,  Michael H. Cohen

    IPC: G10L15/26 ,  G10L15/00 ,  G10L15/197 ,  G10L15/22

    CPC classification number: G06F17/30696 ,  G06F17/30241 ,  G06F17/30292 ,  G06F17/30684 ,  G06F17/30687 ,  G10L15/005 ,  G10L15/14 ,  G10L15/197 ,  G10L15/24 ,  G10L15/26 ,  G10L15/265 ,  G10L2015/0633 ,  G10L2015/081 ,  G10L2015/228

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.

    Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的用于语音识别的计算机程序。 方法之一包括接收用于语音识别的基本语言模型，其包括具有基本概率值的第一字序列; 接收与查询语境相关联的语音搜索查询; 当查询上下文满足与定制语言模型相关联的一个或多个标准时，确定要使用定制语言模型; 获得定制语言模型，包括具有调整概率值的第一单词序列的定制语言模型是根据查询语境调整的基本概率值; 以及基于一个或多个概率将所述语音搜索查询转换为文本搜索查询，所述概率中的每一个对应于一个或多个单词序列的组中的单词序列，所述组包括具有调整后的概率值的第一单词序列。

Patent Agency Ranking