中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.018 seconds)

    Method and apparatus for determining output token
    1.
    发明授权
    Method and apparatus for determining output token 有权

    公开(公告)号：US11574190B2

    公开(公告)日：2023-02-07

    申请号：US16851300

    申请日：2020-04-17

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Min-Joong Lee

    IPC: G06N3/08 ,  G06N20/20 ,  G06F17/18 ,  G06K9/62 ,  G06N3/04

    Abstract: A method for determining an output token includes predicting a first probability of each of candidate output tokens of a first model, predicting a second probability of each of the candidate output tokens of a second model interworking with the first model, adjusting the second probability of each of the candidate output tokens based on the first probability, and determining the output token among the candidate output tokens based on the first probability and the adjusted second probability.

    Decoding method and apparatus in artificial neural network for speech recognition
    2.
    发明授权
    Decoding method and apparatus in artificial neural network for speech recognition 有权

    公开(公告)号：US12100392B2

    公开(公告)日：2024-09-24

    申请号：US18321876

    申请日：2023-05-23

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Min-Joong Lee ,  Tae Gyoon Kang

    IPC: G10L15/16

    CPC classification number: G10L15/16

    Abstract: A decoding method and apparatus in an artificial neural network for speech recognition. The decoding method in the artificial neural network for speech recognition includes performing a first decoding task of decoding a feature including speech information and at least one token recognized up to current time, using a shared decoding layer included in the artificial neural network, performing a second decoding task of decoding the at least one token, using the shared decoding layer, and determining an output token to be recognized subsequent to the at least one token based on a result of the first decoding task and a result of the second decoding task.

    Apparatus and method with classification
    3.
    发明授权
    Apparatus and method with classification 有权

    公开(公告)号：US11100374B2

    公开(公告)日：2021-08-24

    申请号：US16671639

    申请日：2019-11-01

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Young-Seok Kim ,  Hwidong Na ,  Seongmin Ok ,  Min-Joong Lee

    IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04

    Abstract: A processor-implemented classification method includes: determining a first probability vector including a first probability, for each of a plurality of classes, resulting from a classification of an input with respect to the classes; determining, based on the determined first probability vector, whether one or more of the classes represented in the first probability vector are confusing classes; adjusting, in response to one or more of the classes being the confusing classes, the determined first probability vector based on a first probability of each of the confusing classes and a maximum value of the first probabilities; determining a second probability vector including a second probability, for each of the classes, resulting from another classification of the input with respect to the classes; and performing classification on the input based on a result of a comparison between the determined second probability vector and the adjusted first probability vector.

    Decoding method and apparatus in artificial neural network for speech recognition
    5.
    发明授权
    Decoding method and apparatus in artificial neural network for speech recognition 有权

    公开(公告)号：US11694677B2

    公开(公告)日：2023-07-04

    申请号：US16844401

    申请日：2020-04-09

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Min-Joong Lee ,  Tae Gyoon Kang

    IPC: G10L15/16

    CPC classification number: G10L15/16

    Abstract: A decoding method and apparatus in an artificial neural network for speech recognition. The decoding method in the artificial neural network for speech recognition includes performing a first decoding task of decoding a feature including speech information and at least one token recognized up to current time, using a shared decoding layer included in the artificial neural network, performing a second decoding task of decoding the at least one token, using the shared decoding layer, and determining an output token to be recognized subsequent to the at least one token based on a result of the first decoding task and a result of the second decoding task.

    Method and apparatus with speech recognition
    9.
    发明授权
    Method and apparatus with speech recognition 有权

    公开(公告)号：US11361757B2

    公开(公告)日：2022-06-14

    申请号：US16388930

    申请日：2019-04-19

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Min-Joong Lee

    IPC: G10L15/16 ,  G06F40/284 ,  G06F40/274

    Abstract: A processor-implemented decoding method in a first neural network is provided. The method predicts probabilities of candidates of an output token based on at least one previously input token, determines the output token among the candidates based on the predicted probabilities; and determines a next input token by selecting one of the output token and a pre-defined special token based on a determined probability of the output token.

Patent Agency Ranking