利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

14 条记录 (耗时 0.019 秒)

    Automatic language model update
    2.
    发明授权
    Automatic language model update 有权

    公开(公告)号：US10410627B2

    公开(公告)日：2019-09-10

    申请号：US15922154

    申请日：2018-03-15

    申请人： Google LLC

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

    IPC分类号： G10L15/00 ,  G10L17/00 ,  G10L15/065 ,  G10L15/187 ,  G10L15/06 ,  G10L15/26

    摘要： 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.

    Automatic Language Model Update
    5.
    发明申请
    Automatic Language Model Update 审中-公开

    公开(公告)号：US20180204565A1

    公开(公告)日：2018-07-19

    申请号：US15922154

    申请日：2018-03-15

    申请人： Google LLC

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

    IPC分类号： G10L15/065 ,  G10L15/26 ,  G10L15/06 ,  G10L15/187

    CPC分类号： G10L15/065 ,  G10L15/06 ,  G10L15/063 ,  G10L15/187 ,  G10L15/26 ,  G10L2015/0635

    摘要： 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
    9.
    发明授权
    Dynamic language model 有权

    公开(公告)号：US10380160B2

    公开(公告)日：2019-08-13

    申请号：US16200531

    申请日：2018-11-26

    申请人： Google, LLC

    发明人： Pedro J. Moreno Mengibar ,  Michael H. Cohen

    IPC分类号： G06K9/00 ,  G10L25/00 ,  G06F16/338 ,  G06F16/33 ,  G10L15/00 ,  G06F16/21 ,  G06F16/29 ,  G10L15/14 ,  G10L15/197 ,  G10L15/24 ,  G10L15/26 ,  G10L15/06 ,  G10L15/22 ,  G10L15/08

    摘要： 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.