中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

25 records (took 0.017 seconds)

    ENCODER-DECODER MODELS FOR SEQUENCE TO SEQUENCE MAPPING
    11.
    发明申请
    ENCODER-DECODER MODELS FOR SEQUENCE TO SEQUENCE MAPPING 审中-公开

    公开(公告)号：US20190057683A1

    公开(公告)日：2019-02-21

    申请号：US15846634

    申请日：2017-12-19

    Applicant: Google LLC

    Inventor： Hasim Sak ,  Sean Matthew Shannon

    IPC: G10L15/16 ,  G06N3/02 ,  G06N3/08 ,  G10L15/22 ,  G10L15/14 ,  G10L15/02 ,  G10L15/183 ,  G10L15/06

    Abstract: Methods, systems, and apparatus for performing speech recognition. In some implementations, acoustic data representing an utterance is obtained. The acoustic data corresponds to time steps in a series of time steps. One or more computers process scores indicative of the acoustic data using a recurrent neural network to generate a sequence of outputs. The sequence of outputs indicates a likely output label from among a predetermined set of output labels. The predetermined set of output labels includes output labels that respectively correspond to different linguistic units and to a placeholder label that does not represent a classification of acoustic data. The recurrent neural network is configured to use an output label indicated for a previous time step to determine an output label for the current time step. The generated sequence of outputs is processed to generate a transcription of the utterance, and the transcription of the utterance is provided.

    Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
    12.
    发明申请
    Variational Embedding Capacity in Expressive End-to-End Speech Synthesis 有权

    公开(公告)号：US20240395238A1

    公开(公告)日：2024-11-28

    申请号：US18796738

    申请日：2024-08-07

    Applicant: Google LLC

    Inventor： Eric Dean Battenberg ,  Daisy Stanton ,  Russell John Wyatt Skerry-Ryan ,  Soroosh Mariooryad ,  David Teh-hwa Kao ,  Thomas Edward Bagby ,  Sean Matthew Shannon

    IPC: G10L13/047 ,  G10L13/10

    Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.

    Variational embedding capacity in expressive end-to-end speech synthesis
    15.
    发明授权
    Variational embedding capacity in expressive end-to-end speech synthesis 有权

    公开(公告)号：US11646010B2

    公开(公告)日：2023-05-09

    申请号：US17643455

    申请日：2021-12-09

    Applicant: Google LLC

    Inventor： Eric Dean Battenberg ,  Daisy Stanton ,  Russell John Wyatt Skerry-Ryan ,  Soroosh Mariooryad ,  David Teh-Hwa Kao ,  Thomas Edward Bagby ,  Sean Matthew Shannon

    IPC: G10L25/63 ,  G06F40/30 ,  G10L13/047 ,  G10L13/10

    CPC classification number: G10L13/047 ,  G10L13/10

    Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.

    Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
    16.
    发明申请
    Variational Embedding Capacity in Expressive End-to-End Speech Synthesis 有权

    公开(公告)号：US20220101826A1

    公开(公告)日：2022-03-31

    申请号：US17643455

    申请日：2021-12-09

    Applicant: Google LLC

    Inventor： Eric Dean Battenberg ,  Daisy Stanton ,  Russell John Wyatt Skerry-Ryan ,  Soroosh Mariooryad ,  David Teh-Hwa Kao ,  Thomas Edward Bagby ,  Sean Matthew Shannon

    IPC: G10L13/047 ,  G10L13/10

    Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.

    Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
    17.
    发明申请
    Variational Embedding Capacity in Expressive End-to-End Speech Synthesis 审中-公开

    公开(公告)号：US20200372897A1

    公开(公告)日：2020-11-26

    申请号：US16879714

    申请日：2020-05-20

    Applicant: Google LLC

    Inventor： Eric Dean Battenberg ,  Daisy Stanton ,  Russell John Wyatt Skerry-Ryan ,  Soroosh Mariooryad ,  David Teh-hwa Kao ,  Thomas Edward Bagby ,  Sean Matthew Shannon

    IPC: G10L13/047 ,  G10L13/10

    Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.

    END OF QUERY DETECTION
    18.
    发明申请
    END OF QUERY DETECTION 审中-公开

    公开(公告)号：US20180350395A1

    公开(公告)日：2018-12-06

    申请号：US16001140

    申请日：2018-06-06

    Applicant: Google LLC

    Inventor： Gabor Simko ,  Maria Carolina Parada San Martin ,  Sean Matthew Shannon

    IPC: G10L25/78 ,  G10L15/187 ,  G10L15/22

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting an end of a query are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance spoken by a user. The actions further include applying, to the audio data, an end of query model. The actions further include determining the confidence score that reflects a likelihood that the utterance is a complete utterance. The actions further include comparing the confidence score that reflects the likelihood that the utterance is a complete utterance to a confidence score threshold. The actions further include determining whether the utterance is likely complete or likely incomplete. The actions further include providing, for output, an instruction to (i) maintain a microphone that is receiving the utterance in an active state or (ii) deactivate the microphone that is receiving the utterance.

    ENCODER-DECODER MODELS FOR SEQUENCE TO SEQUENCE MAPPING
    20.
    发明公开
    ENCODER-DECODER MODELS FOR SEQUENCE TO SEQUENCE MAPPING 审中-公开

    公开(公告)号：US20230410796A1

    公开(公告)日：2023-12-21

    申请号：US18460017

    申请日：2023-09-01

    Applicant: GOOGLE LLC

    Inventor： Hasim Sak ,  Sean Matthew Shannon

    IPC: G10L15/16 ,  G06N3/02 ,  G06N3/084 ,  G10L15/22 ,  G10L15/14 ,  G06N3/044 ,  G06N3/045

    CPC classification number: G10L15/16 ,  G06N3/02 ,  G06N3/084 ,  G10L15/22 ,  G10L15/14 ,  G06N3/044 ,  G06N3/045 ,  G10L2015/025

    Abstract: Methods, systems, and apparatus for performing speech recognition. In some implementations, acoustic data representing an utterance is obtained. The acoustic data corresponds to time steps in a series of time steps. One or more computers process scores indicative of the acoustic data using a recurrent neural network to generate a sequence of outputs. The sequence of outputs indicates a likely output label from among a predetermined set of output labels. The predetermined set of output labels includes output labels that respectively correspond to different linguistic units and to a placeholder label that does not represent a classification of acoustic data. The recurrent neural network is configured to use an output label indicated for a previous time step to determine an output label for the current time step. The generated sequence of outputs is processed to generate a transcription of the utterance, and the transcription of the utterance is provided.

Patent Agency Ranking