中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

56 records (took 0.054 seconds)

    Fast, language-independent method for user authentication by voice
    31.
    发明授权
    Fast, language-independent method for user authentication by voice 有权
    快速，语言独立的方法，用于通过语音进行用户认证

    公开(公告)号：US09218809B2

    公开(公告)日：2015-12-22

    申请号：US14151605

    申请日：2014-01-09

    Applicant: Apple Inc.

    Inventor： Jerome R. Bellegarda ,  Kim E. A. Silverman

    IPC: G10L15/07 ,  G10L17/04

    CPC classification number: G10L17/22 ,  G10L15/07 ,  G10L17/04 ,  G10L17/08 ,  G10L17/14

    Abstract: A method and system for training a user authentication by voice signal are described. In one embodiment, a set of feature vectors are decomposed into speaker-specific recognition units. The speaker-specific recognition units are used to compute distribution values to train the voice signal. In addition, spectral feature vectors are decomposed into speaker-specific characteristic units which are compared to the speaker-specific distribution values. If the speaker-specific characteristic units are within a threshold limit of the speaker-specific distribution values, the speech signal is authenticated.

    Abstract translation: 描述了通过语音信号训练用户认证的方法和系统。 在一个实施例中，一组特征向量被分解成说话者特定的识别单元。 扬声器特定识别单元用于计算分配值以训练语音信号。 此外，频谱特征向量被分解成与特定于扬声器的分布值相比较的扬声器特定特征单元。 如果扬声器特有特征单元在扬声器特定分布值的阈值限度内，则认证语音信号。

    Analysis and validation of language models
    32.
    发明授权
    Analysis and validation of language models 有权

    公开(公告)号：US11829720B2

    公开(公告)日：2023-11-28

    申请号：US17108933

    申请日：2020-12-01

    Applicant: Apple Inc.

    Inventor： Jerome R. Bellegarda ,  Bishal Barman ,  Brent D. Ramerth

    IPC: G06F40/284 ,  G06N20/00 ,  G06F40/40

    CPC classification number: G06F40/284 ,  G06F40/40 ,  G06N20/00

    Abstract: Systems and methods for analysis and validation of language models trained using data that is unavailable or inaccessible are provided. One example method includes, at an electronic device with one or more processors and memory, obtaining a first set of data corresponding to one or more tokens predicted based on one or more previous tokens. The method determines a probability that the first set of data corresponds to a prediction generated by a first language model trained using a user privacy preserving training process. In accordance with a determination that the probability is within a predetermined range, the method determines that the one or more tokens correspond to a prediction associated with the user privacy preserving training process and outputs a predicted token sequence including the one or more tokens and the one or more previous tokens.

    Word prediction with multiple overlapping contexts
    33.
    发明授权
    Word prediction with multiple overlapping contexts 有权

    公开(公告)号：US11797766B2

    公开(公告)日：2023-10-24

    申请号：US17327415

    申请日：2021-05-21

    Applicant: Apple Inc.

    Inventor： Jerome R. Bellegarda ,  Richard Harry Starfield

    IPC: G06F40/274 ,  G06F3/023 ,  G06F40/35 ,  G06F40/242

    CPC classification number: G06F40/274 ,  G06F3/0237 ,  G06F40/242 ,  G06F40/35

    Abstract: Systems and processes for word prediction using multiple contexts are provided. For example, a plurality of words are received. A first word context including a first plurality of received words, and a second word context corresponding to the first plurality of received words and a second plurality of received words, are obtained. A first current word probability is determined based on a first language model using the first word context. A second current word probability is determined based on a second language model using the second word context. A third current word probability is determined based on the second language model using the first word context. A fourth current word probability is determined based on the first current word probability, the second current word probability, and the third current word probability. An output is provided, to a user, including a current word prediction based on the fourth current word probability.

    Incorporating user feedback into text prediction models via joint reward planning
    35.
    发明授权
    Incorporating user feedback into text prediction models via joint reward planning 有权

    公开(公告)号：US11181988B1

    公开(公告)日：2021-11-23

    申请号：US17008265

    申请日：2020-08-31

    Applicant: Apple Inc.

    Inventor： Jerome R. Bellegarda ,  Akash Mehra

    IPC: G06N3/08 ,  G06F3/023 ,  G06F40/284 ,  G06F3/0481 ,  G06F3/0488

    Abstract: An example process includes: obtaining input token(s); determining, using a joint prediction model, based on the input token(s): a first predicted token following the input token(s) and a second predicted token following the first predicted token; and a first user action to be performed on the first predicted token, where determining the first user action includes: determining a first reward value for performing the first user action based on a first current reward value for performing the first user action and a second reward value for performing a second user action on the second predicted token; outputting the first predicted token; detecting a user action performed on the first predicted token; and in accordance with a determination that the detected user action does not match the first user action: causing parameters of the joint prediction model to be updated, the parameters being configured to determine the first user action.

    Neural typographical error modeling via generative adversarial networks
    36.
    发明授权
    Neural typographical error modeling via generative adversarial networks 有权

    公开(公告)号：US11170166B2

    公开(公告)日：2021-11-09

    申请号：US16228496

    申请日：2018-12-20

    Applicant: Apple Inc.

    Inventor： Jerome R. Bellegarda ,  Giulia Pagallo

    IPC: G06F40/232 ,  G06N3/08 ,  G06N3/04 ,  G06F40/30

    Abstract: Systems and processes for operating an intelligent automated assistant are provided. In one example process, one or more input words can be received. The process can extract, based on the one or more input words, seed data for unsupervised training of a first learning network. Training data that includes a collection of words having typographical errors for the first learning network can be obtained. The process can determine, using the first learning network and based on the seed data and the training data, one or more output words having a probability distribution corresponding to a probability distribution of the training data. The one or more output words can include typographical errors. The process can generate, based on the determined one or more output words, a data set for supervised training of a second learning network. The second learning network can provide one or more typographical error suggestions.

Patent Agency Ranking