知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

19 records (took 0.027 seconds)

    SYSTEMS AND METHODS FOR NAME PRONUNCIATION
    1.
    发明申请
    SYSTEMS AND METHODS FOR NAME PRONUNCIATION 有权

    公开(公告)号：US20210327409A1

    公开(公告)日：2021-10-21

    申请号：US17364589

    申请日：2021-06-30

    Applicant: Apple Inc.

    Inventor： Devang K. NAIK

    IPC: G10L13/08 ,  G10L15/187

    Abstract: Systems and methods are provided for associating a phonetic pronunciation with a name by receiving the name, mapping the name to a plurality of monosyllabic components that are combinable to construct the phonetic pronunciation of the name, receiving a user input to select one or more of the plurality, and combining the selected one or more of the plurality of monosyllabic components to construct the phonetic pronunciation of the name.

    MEMORY-EFFICIENT DIFFERENTIABLE WEIGHT CLUSTERING FOR LARGE LANGUAGE MODEL COMPRESSION
    5.
    发明申请
    MEMORY-EFFICIENT DIFFERENTIABLE WEIGHT CLUSTERING FOR LARGE LANGUAGE MODEL COMPRESSION 有权

    公开(公告)号：US20250037018A1

    公开(公告)日：2025-01-30

    申请号：US18658919

    申请日：2024-05-08

    Applicant: Apple Inc.

    Inventor： Minsik CHO ,  Keivan ALIZADEH VAHID ,  Qichen FU ,  Saurabh ADYA ,  Carlo Eduardo Cabanero DEL MUNDO ,  Mohammad RASTEGARI ,  Devang K. NAIK ,  Peter ZATLOUKAL

    IPC: G06N20/00

    Abstract: The subject technology provides memory-efficient differentiable weight clustering for large language model compression. An apparatus determines a tensor including an attention map between learned weights of a trained machine learning model and corresponding centroids. The apparatus also determines a compressed attention table and a plurality of index lists during compression of the trained machine learning model based on an uniquification of the attention map and sharding of an associated index list. The apparatus determines whether the tensor exists at a destination device during compression of the trained machine learning model using a marshaling layer. The apparatus refrains from copying the tensor to the destination device when the tensor exists at the destination device, or copies the tensor to the destination device when the tensor does not exist at the destination device. The apparatus deploys a compressed machine learning model based on the compression of the trained machine learning model.

    DEVICE, METHOD, AND GRAPHICAL USER INTERFACE FOR INTEGRATING RECOGNITION OF HANDWRITING GESTURES WITH A SCREEN READER
    7.
    发明申请
    DEVICE, METHOD, AND GRAPHICAL USER INTERFACE FOR INTEGRATING RECOGNITION OF HANDWRITING GESTURES WITH A SCREEN READER 审中-公开
    用屏幕阅读器集成手写识别手段的设备，方法和图形用户界面

    公开(公告)号：US20150040213A1

    公开(公告)日：2015-02-05

    申请号：US14517691

    申请日：2014-10-17

    Applicant: Apple Inc.

    Inventor： Christopher B. FLEIZACH ,  Darren C. MINIFIE ,  Gregory F. HUGHES ,  Ryan N. DOUR ,  Ian M. FISCH ,  Joel M. LOPES DA SILVA ,  Michael M. PEDERSEN, II ,  Eric T. SEYMOUR ,  Devang K. NAIK ,  Ryan S. DIXON

    IPC: G06F21/36 ,  G06F3/01 ,  G06F3/0481 ,  G06F3/0488

    CPC classification number: G06F3/04883 ,  G06F3/017 ,  G06F3/0481 ,  G06F3/04817 ,  G06F3/0488 ,  G06F3/04886 ,  G06F3/167 ,  G06F21/36

    Abstract: While an electronic device with a display and a touch-sensitive surface is in a screen reader accessibility mode, the device displays an application launcher screen including a plurality of application icons. A respective application icon corresponds to a respective application stored in the device. The device detects a sequence of one or more gestures on the touch-sensitive surface that correspond to one or more characters. A respective gesture that corresponds to a respective character is a single finger gesture that moves across the touch-sensitive surface along a respective path that corresponds to the respective character. The device determines whether the detected sequence of one or more gestures corresponds to a respective application icon of the plurality of application icons, and, in response to determining that the detected sequence of one or more gestures corresponds to the respective application icon, performs a predefined operation associated with the respective application icon.

    Abstract translation: 虽然具有显示器和触敏表面的电子设备处于屏幕阅读器可访问性模式中，但是该设备显示包括多个应用图标的应用启动器屏幕。 相应的应用图标对应于存储在设备中的相应应用。 设备检测对应于一个或多个字符的触敏表面上的一个或多个手势的序列。 对应于相应字符的相应手势是沿着对应于相应字符的相应路径跨越触敏表面移动的单个手指手势。 所述设备确定检测到的一个或多个手势的序列是否对应于多个应用图标的相应应用图标，并且响应于确定所检测的一个或多个手势的序列对应于相应的应用图标，执行预定义的 与相应的应用程序图标相关的操作。

    METHOD FOR EXTRACTING SALIENT DIALOG USAGE FROM LIVE DATA
    9.
    发明申请
    METHOD FOR EXTRACTING SALIENT DIALOG USAGE FROM LIVE DATA 有权

    公开(公告)号：US20220214775A1

    公开(公告)日：2022-07-07

    申请号：US17703308

    申请日：2022-03-24

    Applicant: Apple Inc.

    Inventor： Rushin N. SHAH ,  Devang K. NAIK

    IPC: G06F3/0481 ,  G06F40/295

    Abstract: Systems and processes are disclosed for virtual assistant request recognition using live usage data and data relating to future events. User requests that are received but not recognized can be used to generate candidate request templates. A count can be associated with each candidate request template and can be incremented each time a matching candidate request template is received. When a count reaches a threshold level, the corresponding candidate request template can be used to train a virtual assistant to recognize and respond to similar user requests in the future. In addition, data relating to future events can be mined to extract relevant information that can be used to populate both recognized user request templates and candidate user request templates. Populated user request templates (e.g., whole expected utterances) can then be used to recognize user requests and disambiguate user intent as future events become relevant.

    REDUCING DEVICE PROCESSING OF UNINTENDED AUDIO
    10.
    发明申请
    REDUCING DEVICE PROCESSING OF UNINTENDED AUDIO 有权

    公开(公告)号：US20220093095A1

    公开(公告)日：2022-03-24

    申请号：US17123428

    申请日：2020-12-16

    Applicant: Apple Inc.

    Inventor： Pranay DIGHE ,  Erik MARCHI ,  Srikanth VISHNUBHOTLA ,  Sachin KAJAREKAR ,  Devang K. NAIK

    IPC: G10L15/22 ,  G10L15/26 ,  G10L15/30

    Abstract: An example process includes: receiving an audio stream; determining a plurality of acoustic representations of the audio stream, where each acoustic representation of the plurality of acoustic representations corresponds to a respective frame of the audio stream; obtaining a respective plurality of scores indicating whether each respective frame of the audio stream is directed to an electronic device, where the obtaining includes: determining, using a triggering model operating on the electronic device, for each acoustic representation, a score indicating whether the respective frame of the audio stream is directed to the electronic device; determining, based on the respective plurality of scores, a likelihood that the audio stream is directed to the electronic device; determining whether the likelihood is above or below a threshold; and in response to determining that the likelihood is below the threshold, ceasing to process the audio stream.

Patent Agency Ranking