知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

4 条记录 (耗时 0.012 秒)

    AUDIO SOURCE SEPARATION FOR AUDIO DEVICES
    1.
    发明申请
    AUDIO SOURCE SEPARATION FOR AUDIO DEVICES 有权

    公开(公告)号：US20220270629A1

    公开(公告)日：2022-08-25

    申请号：US17589889

    申请日：2022-01-31

    申请人： Apple Inc.

    发明人： Carlos M. AVENDANO ,  John WOODRUFF ,  Jonathan HUANG ,  Mehrez SOUDEN ,  Andreas KOUTROUVELIS

    IPC分类号： G10L21/028 ,  H04R1/10 ,  G10L21/0232 ,  G06N20/00

    摘要： Implementations of the subject technology provide systems and methods for providing audio source separation for audio input, such as for audio devices having limited power and/or computing resources. The subject technology may allow an audio device to leverage processing and/or power resources of a companion device that is communicatively coupled to the audio device. The companion device may identify a noise condition of the audio device, select a source separation model based on the noise condition, and provide the source separation model to the audio device. In this way, the audio device can provide audio source separation functionality using a relatively small footprint source separation model that is specific to the noise condition in which the audio device is operated.

    EFFICIENT EMBEDDING FOR ACOUSTIC MODELS
    2.
    发明公开
    EFFICIENT EMBEDDING FOR ACOUSTIC MODELS 审中-公开

    公开(公告)号：US20230360641A1

    公开(公告)日：2023-11-09

    申请号：US17736959

    申请日：2022-05-04

    申请人： Apple Inc.

    发明人： Daniel C. KLINGLER ,  Carlos M. AVENDANO ,  Jonathan HUANG ,  Miquel ESPI MARQUES

    IPC分类号： G10L15/08 ,  G10L25/78 ,  G10L25/51 ,  G06N20/20

    CPC分类号： G10L15/08 ,  G10L25/78 ,  G10L25/51 ,  G06N20/20

    摘要： The subject disclosure provides systems and methods for generating and storing learned embeddings of audio inputs to an electronic device. The electronic device may generate and store encoded versions of audio inputs and learned embeddings of the audio inputs. When a new audio input is obtained, the electronic device can generate an encoded version of the new audio input, compare the encoded version of the new audio input to the stored encoded versions of prior audio inputs, and if the encoded version of the new audio input matches one of the stored encoded versions of the prior audio inputs, the electronic device can provide a stored learned embedding that corresponds to the one of the stored encoded versions of the prior audio inputs to a detection model at the electronic device. The cached embeddings can be provided to locally trained models for detecting individual sounds using electronic devices.

    SOUND DETECTION FOR ELECTRONIC DEVICES
    4.
    发明申请
    SOUND DETECTION FOR ELECTRONIC DEVICES 有权

    公开(公告)号：US20220391758A1

    公开(公告)日：2022-12-08

    申请号：US17737017

    申请日：2022-05-04

    申请人： Apple Inc.

    发明人： Jonathan HUANG ,  Miquel ESPI MARQUES ,  Carlos M. AVENDANO ,  Kevin M. DURAND ,  David FINDLAY ,  Vasudha KOWTHA ,  Daniel C. KLINGLER ,  Yichi ZHANG

    IPC分类号： G06N20/00 ,  G06F3/16 ,  H04R1/08 ,  G08B21/18

    摘要： The subject disclosure provides systems and methods for providing locally trained models for detecting individual sounds using electronic devices. Local detection of individual sounds with a detection model at an electronic device can be provided by obtaining training samples for the detection model with the electronic device, and generating additional negative and positive training samples based on the obtained training samples. A two-stage detection process may be provided, in which a trigger model at a device compares an audio input to a reference sound to trigger a detection model at the device. The detection of individual sounds with a detection model at an electronic device can also leverage audio capture capabilities of multiple devices in an acoustic scene to capture multiple concurrent training samples.