利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

439 records (took 0.022 seconds)

    Updating machine learning models across devices
    81.
    发明授权
    Updating machine learning models across devices 有权

    公开(公告)号：US12094451B1

    公开(公告)日：2024-09-17

    申请号：US17677614

    申请日：2022-02-22

    Applicant: Amazon Technologies, Inc.

    Inventor： Tao Zhang ,  Jie Ding ,  Huili Chen

    IPC: G10L15/05 ,  G06N20/20 ,  G10L15/06

    CPC classification number: G10L15/05 ,  G06N20/20 ,  G10L15/063 ,  G10L2015/0635

    Abstract: A system may create a localized machine learning model including one or more customized local parameter values using a global model and variance data. The localized machine learning model may be used by a device or cohort of devices to perform evaluations of data. The localized model may be trained based off a global model that is adjusted and then trained a certain number of steps, where the number of steps is based at least in part on the variance data. The variance data may include variance data from other device cohorts which is received from a remote device, which can also re-train the global model using the variance data and/or the localized machine learning model(s).

    SYSTEMS AND METHODS FOR CONTINUAL LEARNING FOR END TO-END AUTOMATIC SPEECH RECOGNITION
    83.
    发明公开
    SYSTEMS AND METHODS FOR CONTINUAL LEARNING FOR END TO-END AUTOMATIC SPEECH RECOGNITION 审中-公开

    公开(公告)号：US20240290319A1

    公开(公告)日：2024-08-29

    申请号：US18442974

    申请日：2024-02-15

    Applicant: JPMORGAN CHASE BANK, N.A.

    Inventor： Peter PLANTINGA ,  Jaekwon YOO ,  Chandra DHIR

    IPC: G10L15/06

    CPC classification number: G10L15/063 ,  G10L2015/0635

    Abstract: In some aspects, the techniques described herein relate to a method including: providing, to a parallel model training platform, a plurality of domain datasets; training, by the parallel model training platform, a plurality of generalist models in parallel, wherein each generalist model of the plurality of generalist models is trained in parallel using a corresponding one of the plurality of domain datasets, and wherein training the plurality of generalist models in parallel generates a corresponding expert model for each generalist model in the plurality of generalist models; executing, by the parallel model training platform, a model parameter averaging process, wherein the model parameter averaging process take each corresponding expert model as input; and generating, by the parallel model training platform and as output of the model parameter averaging process, an average-of-domain-experts (AoDE) model.

    TRAINING AND TESTING UTTERANCE-BASED FRAMEWORKS
    88.
    发明公开
    TRAINING AND TESTING UTTERANCE-BASED FRAMEWORKS 审中-公开

    公开(公告)号：US20240203401A1

    公开(公告)日：2024-06-20

    申请号：US18530702

    申请日：2023-12-06

    Applicant: Spotify AB

    Inventor： Daniel Bromand

    IPC: G10L15/06 ,  G06F7/58 ,  G10L13/02 ,  G10L15/07

    CPC classification number: G10L15/063 ,  G06F7/582 ,  G10L13/02 ,  G10L15/07 ,  G10L2015/0635

    Abstract: Systems, methods, and devices for training and testing utterance based frameworks are disclosed. The training and testing can be conducting using synthetic utterance samples in addition to natural utterance samples. The synthetic utterance samples can be generated based on a vector space representation of natural utterances. In one method, a synthetic weight vector associated with a vector space is generated. An average representation of the vector space is added to the synthetic weight vector to form a synthetic feature vector. The synthetic feature vector is used to generate a synthetic voice sample. The synthetic voice sample is provided to the utterance-based framework as at least one of a testing or training sample.

    MODEL TRAINING METHOD, SPEECH RECOGNITION METHOD, DEVICE, MEDIUM, AND APPARATUS
    90.
    发明公开
    MODEL TRAINING METHOD, SPEECH RECOGNITION METHOD, DEVICE, MEDIUM, AND APPARATUS 审中-公开

    公开(公告)号：US20240127795A1

    公开(公告)日：2024-04-18

    申请号：US18276769

    申请日：2022-05-07

    Applicant: Beijing Youzhuju Network Technology Co., Ltd.

    Inventor： Linhao DONG ,  Zejun MA

    IPC: G10L15/06 ,  G10L15/065

    CPC classification number: G10L15/063 ,  G10L15/065 ,  G10L2015/0635 ,  G10L19/04

    Abstract: A model training method, a speech recognition method and apparatus, a medium, and a device are provided. The speech recognition model including an encoder, a CIF prediction sub-model and a CTC prediction sub-model. The model training method includes: encoding training speech data based on the encoder to obtain an acoustic vector sequence corresponding to the training speech data; obtaining an information amount sequence corresponding to the training speech data based on the acoustic vector sequence and the CIF prediction sub-model; obtaining a target probability sequence based on the acoustic vector sequence and the CTC prediction sub-model; determining a target loss of the speech recognition model based on the information amount sequence and the target probability sequence; and updating, in response to an updating condition being satisfied, a model parameter of the speech recognition model based on the target loss.

Patent Agency Ranking