中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

49 records (took 0.02 seconds)

    Asynchronous optimization for sequence training of neural networks
    21.
    发明授权
    Asynchronous optimization for sequence training of neural networks 有权

    公开(公告)号：US12073823B2

    公开(公告)日：2024-08-27

    申请号：US18506540

    申请日：2023-11-10

    Applicant: Google LLC

    Inventor： Georg Heigold ,  Erik Mcdermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A. U. Bacchiani

    IPC: G10L15/06 ,  G06N3/045 ,  G10L15/16 ,  G10L15/183

    CPC classification number: G10L15/063 ,  G06N3/045 ,  G10L15/16 ,  G10L15/183

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

    SPEECH RECOGNITION USING NEURAL NETWORKS
    22.
    发明公开
    SPEECH RECOGNITION USING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230206909A1

    公开(公告)日：2023-06-29

    申请号：US18177717

    申请日：2023-03-02

    Applicant: Google LLC

    Inventor： Andrew W. Senior ,  Ignacio L. Moreno

    IPC: G10L15/16 ,  G06N3/02

    CPC classification number: G10L15/16 ,  G06N3/02 ,  G10L15/02

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using neural networks. A feature vector that models audio characteristics of a portion of an utterance is received. Data indicative of latent variables of multivariate factor analysis is received. The feature vector and the data indicative of the latent variables is provided as input to a neural network. A candidate transcription for the utterance is determined based on at least an output of the neural network.

    Speech recognition using neural networks
    23.
    发明授权
    Speech recognition using neural networks 有权

    公开(公告)号：US11620991B2

    公开(公告)日：2023-04-04

    申请号：US17154376

    申请日：2021-01-21

    Applicant: Google LLC

    Inventor： Andrew W. Senior ,  Ignacio L. Moreno

    IPC: G10L15/02 ,  G10L15/16 ,  G06N3/02

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using neural networks. A feature vector that models audio characteristics of a portion of an utterance is received. Data indicative of latent variables of multivariate factor analysis is received. The feature vector and the data indicative of the latent variables is provided as input to a neural network. A candidate transcription for the utterance is determined based on at least an output of the neural network.

    ASYNCHRONOUS OPTIMIZATION FOR SEQUENCE TRAINING OF NEURAL NETWORKS
    24.
    发明申请
    ASYNCHRONOUS OPTIMIZATION FOR SEQUENCE TRAINING OF NEURAL NETWORKS 有权

    公开(公告)号：US20220108686A1

    公开(公告)日：2022-04-07

    申请号：US17644362

    申请日：2021-12-15

    Applicant: Google LLC

    Inventor： Georg Heigold ,  Erik McDermott ,  Vincent O. VanHoucke ,  Andrew W. Senior ,  Michiel A.U. Bacchiani

    IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

    Asynchronous optimization for sequence training of neural networks
    25.
    发明授权
    Asynchronous optimization for sequence training of neural networks 有权

    公开(公告)号：US11227582B2

    公开(公告)日：2022-01-18

    申请号：US17143140

    申请日：2021-01-06

    Applicant: Google LLC

    Inventor： Georg Heigold ,  Erik Mcdermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A. U. Bacchiani

    IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

    Generating representations of acoustic sequences
    27.
    发明授权
    Generating representations of acoustic sequences 有权

    公开(公告)号：US10134393B2

    公开(公告)日：2018-11-20

    申请号：US15664153

    申请日：2017-07-31

    Applicant: Google LLC

    Inventor： Hasim Sak ,  Andrew W. Senior

    IPC: G10L15/16 ,  G06N3/02 ,  G10L15/02 ,  G10L15/14

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representation of acoustic sequences. One of the methods includes: receiving an acoustic sequence, the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; processing the acoustic feature representation at an initial time step using an acoustic modeling neural network; for each subsequent time step of the plurality of time steps: receiving an output generated by the acoustic modeling neural network for a preceding time step, generating a modified input from the output generated by the acoustic modeling neural network for the preceding time step and the acoustic representation for the time step, and processing the modified input using the acoustic modeling neural network to generate an output for the time step; and generating a phoneme representation for the utterance from the outputs for each of the time steps.

    Training acoustic models using connectionist temporal classification
    29.
    发明授权
    Training acoustic models using connectionist temporal classification 有权

    公开(公告)号：US11341958B2

    公开(公告)日：2022-05-24

    申请号：US17022224

    申请日：2020-09-16

    Applicant: Google LLC

    Inventor： Kanury Kanishka Rao ,  Andrew W. Senior ,  Hasim Sak

    IPC: G10L15/16 ,  G10L15/187 ,  G10L15/30 ,  G10L15/02

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training acoustic models and using the trained acoustic models. A connectionist temporal classification (CTC) acoustic model is accessed, the CTC acoustic model having been trained using a context-dependent state inventory generated from approximate phonetic alignments determined by another CTC acoustic model trained without fixed alignment targets. Audio data for a portion of an utterance is received. Input data corresponding to the received audio data is provided to the accessed CTC acoustic model. Data indicating a transcription for the utterance is generated based on output that the accessed CTC acoustic model produced in response to the input data. The data indicating the transcription is provided as output of an automated speech recognition service.

    SPEECH RECOGNITION USING NEURAL NETWORKS
    30.
    发明申请
    SPEECH RECOGNITION USING NEURAL NETWORKS 有权

    公开(公告)号：US20210183376A1

    公开(公告)日：2021-06-17

    申请号：US17154376

    申请日：2021-01-21

    Applicant: Google LLC

    Inventor： Andrew W. Senior ,  Ignacio L. Moreno

    IPC: G10L15/16 ,  G06N3/02

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using neural networks. A feature vector that models audio characteristics of a portion of an utterance is received. Data indicative of latent variables of multivariate factor analysis is received. The feature vector and the data indicative of the latent variables is provided as input to a neural network. A candidate transcription for the utterance is determined based on at least an output of the neural network.

Patent Agency Ranking