利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

14 条记录 (耗时 0.017 秒)

    LEARNING TO EXTRACT ENTITIES FROM CONVERSATIONS WITH NEURAL NETWORKS
    1.
    发明申请
    LEARNING TO EXTRACT ENTITIES FROM CONVERSATIONS WITH NEURAL NETWORKS 有权

    公开(公告)号：US20220075944A1

    公开(公告)日：2022-03-10

    申请号：US17432259

    申请日：2020-02-19

    申请人： Google LLC

    发明人： Nan Du ,  Linh Trans ,  Yu-hui Chen ,  Izhak Shafran

    IPC分类号： G06F40/284 ,  G06F40/295 ,  G06N3/04

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for extracting entities from conversation transcript data. One of the methods includes obtaining a conversation transcript sequence, processing the conversation transcript sequence using a span detection neural network configured to generate a set of text token spans; and for each text token span: processing a span representation using an entity name neural network to generate an entity name probability distribution over a set of entity names, each probability in the entity name probability distribution representing a likelihood that a corresponding entity name is a name of the entity referenced by the text token span; and processing the span representation using an entity status neural network to generate an entity status probability distribution over a set of entity statuses.

    COMPLEX EVOLUTION RECURRENT NEURAL NETWORKS
    4.
    发明申请
    COMPLEX EVOLUTION RECURRENT NEURAL NETWORKS 审中-公开

    公开(公告)号：US20190156819A1

    公开(公告)日：2019-05-23

    申请号：US16251430

    申请日：2019-01-18

    申请人： Google LLC

    发明人： Izhak Shafran ,  Thomas E. Bagby ,  Russell John Wyatt Skerry-Ryan

    IPC分类号： G10L15/16 ,  G10L19/02 ,  G10L15/02 ,  G10H1/00

    CPC分类号： G10L15/16 ,  G06N3/02 ,  G10H1/00 ,  G10H2210/036 ,  G10H2210/046 ,  G10H2250/235 ,  G10H2250/311 ,  G10L15/02 ,  G10L17/18 ,  G10L19/0212 ,  G10L25/30

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex evolution recurrent neural networks. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A first vector sequence comprising audio features determined from the audio data is generated. A second vector sequence is generated, as output of a first recurrent neural network in response to receiving the first vector sequence as input, where the first recurrent neural network has a transition matrix that implements a cascade of linear operators comprising (i) first linear operators that are complex-valued and unitary, and (ii) one or more second linear operators that are non-unitary. An output vector sequence of a second recurrent neural network is generated. A transcription for the utterance is generated based on the output vector sequence generated by the second recurrent neural network. The transcription for the utterance is provided.

    Complex linear projection for acoustic modeling
    5.
    发明授权
    Complex linear projection for acoustic modeling 有权

    公开(公告)号：US10140980B2

    公开(公告)日：2018-11-27

    申请号：US15386979

    申请日：2016-12-21

    申请人： Google LLC

    发明人： Samuel Bengio ,  Mirko Visontai ,  Christopher Walter George Thornton ,  Michiel A. U. Bacchiani ,  Tara N. Sainath ,  Ehsan Variani ,  Izhak Shafran

    IPC分类号： G10L15/16 ,  G10L19/02 ,  G10L15/02

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

    COMPLEX LINEAR PROJECTION FOR ACOUSTIC MODELING
    7.
    发明申请
    COMPLEX LINEAR PROJECTION FOR ACOUSTIC MODELING 审中-公开

    公开(公告)号：US20200286468A1

    公开(公告)日：2020-09-10

    申请号：US16879322

    申请日：2020-05-20

    申请人： Google LLC

    发明人： Samuel Bengio ,  Mirko Visontai ,  Christopher Walter George Thornton ,  Tara N. Sainath ,  Ehsan Variani ,  Izhak Shafran ,  Michiel A.u. Bacchiani

    IPC分类号： G10L15/16 ,  G10L15/02 ,  G10H1/00 ,  G10L19/02

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

    Complex evolution recurrent neural networks
    8.
    发明授权
    Complex evolution recurrent neural networks 有权

    公开(公告)号：US10529320B2

    公开(公告)日：2020-01-07

    申请号：US16251430

    申请日：2019-01-18

    申请人： Google LLC

    发明人： Izhak Shafran ,  Thomas E. Bagby ,  Russell John Wyatt Skerry-Ryan

    IPC分类号： G10L15/16 ,  G10L19/02 ,  G10L15/02 ,  G10H1/00 ,  G06N3/02 ,  G10L17/18 ,  G10L25/30

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex evolution recurrent neural networks. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A first vector sequence comprising audio features determined from the audio data is generated. A second vector sequence is generated, as output of a first recurrent neural network in response to receiving the first vector sequence as input, where the first recurrent neural network has a transition matrix that implements a cascade of linear operators comprising (i) first linear operators that are complex-valued and unitary, and (ii) one or more second linear operators that are non-unitary. An output vector sequence of a second recurrent neural network is generated. A transcription for the utterance is generated based on the output vector sequence generated by the second recurrent neural network. The transcription for the utterance is provided.