中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.011 seconds)

    SEAMLESS LISTEN-THROUGH FOR A WEARABLE DEVICE
    1.
    发明申请
    SEAMLESS LISTEN-THROUGH FOR A WEARABLE DEVICE 审中-公开

    公开(公告)号：US20200304903A1

    公开(公告)日：2020-09-24

    申请号：US16896010

    申请日：2020-06-08

    Applicant: QUALCOMM Incorporated

    Inventor： Lae-Hoon KIM ,  Dongmei WANG ,  Fatemeh SAKI ,  Taher SHAHBAZI MIRZAHASANLOO ,  Erik VISSER ,  Rogerio Guedes ALVES

    IPC: H04R1/10

    Abstract: Methods, systems, and devices for signal processing are described. Generally, in one example as provided for by the described techniques, a wearable device includes a processor configured to retrieve a plurality of external microphone signals that includes audio sound from outside of the device from a memory; to separate, based on at least information from an internal microphone signal, a self-voice component from a background component; to perform a first listen-through operation on the separated self-voice component to produce a first listen-through signal; and to produce an output audio signal that is based on at least the first listen-through signal, wherein the output audio signal includes an audio zoom signal that includes audio sound of the plurality of external microphone signals.

    ADAPTIVE SOUND EVENT CLASSIFICATION
    3.
    发明申请
    ADAPTIVE SOUND EVENT CLASSIFICATION 有权

    公开(公告)号：US20220165292A1

    公开(公告)日：2022-05-26

    申请号：US17102724

    申请日：2020-11-24

    Applicant: QUALCOMM Incorporated

    Inventor： Fatemeh SAKI ,  Yinyi GUO ,  Erik VISSER

    IPC: G10L25/51 ,  H04R1/08 ,  G06N5/04 ,  G06N20/00

    Abstract: A device includes one or more processors configured to provide audio data samples to a sound event classification model. The one or more processors are also configured to determine, based on an output of the sound event classification model responsive to the audio data samples, whether a sound class of with the audio data samples was recognized by the sound event classification model. The one or more processors are further configured to, based on a determination that the sound class was not recognized, determine whether the sound event classification model corresponds to an audio scene associated with the audio data samples. The one or more processors are also configured to, based on a determination that the sound event classification model corresponds to the audio scene associated with the audio data samples, store model update data based on the audio data samples.

    SEAMLESS LISTEN-THROUGH FOR A WEARABLE DEVICE
    4.
    发明申请
    SEAMLESS LISTEN-THROUGH FOR A WEARABLE DEVICE 有权

    公开(公告)号：US20210204053A1

    公开(公告)日：2021-07-01

    申请号：US17201998

    申请日：2021-03-15

    Applicant: QUALCOMM Incorporated

    Inventor： Lae-Hoon KIM ,  Dongmei WANG ,  Fatemeh SAKI ,  Taher SHAHBAZI MIRZAHASANLOO ,  Erik VISSER ,  Rogerio Guedes ALVES

    IPC: H04R1/10

    Abstract: Methods, systems, and devices for signal processing are described. Generally, as provided for by the described techniques, a wearable device may receive an input audio signal (e.g., including both an external signal and a self-voice signal). The wearable device may detect the self-voice signal in the input audio signal based on a self-voice activity detection (SVAD) procedure, and may implement the described techniques based thereon. The wearable device may perform beamforming operations or other separation procedures to isolate the external signal and the self-voice signal from the input audio signal. The wearable device may apply a first filter to the external signal, and a second filter to the self-voice signal. The wearable device may then mix the filtered signals, and generate an output signal that sounds natural to the user.

    SOUND EVENT DETECTION LEARNING
    5.
    发明申请
    SOUND EVENT DETECTION LEARNING 有权

    公开(公告)号：US20210158837A1

    公开(公告)日：2021-05-27

    申请号：US17102797

    申请日：2020-11-24

    Applicant: QUALCOMM Incorporated

    Inventor： Fatemeh SAKI ,  Yinyi GUO ,  Erik VISSER ,  Eunjeong KOH

    IPC: G10L25/78 ,  G10L25/30 ,  G10L25/24 ,  G06N3/08 ,  G06N3/04 ,  H04R5/033 ,  B60R11/02

    Abstract: A device includes a processor configured to receive audio data samples and provide the audio data samples to a first neural network to generate a first output corresponding to a first set of sound classes. The processor is further configured to provide the audio data samples to a second neural network to generate a second output corresponding to a second set of sound classes. A second count of classes of the second set of sound classes is greater than a first count of classes of the first set of sound classes. The processor is also configured to provide the first output to a neural adapter to generate a third output corresponding to the second set of sound classes. The processor is further configured to provide the second output and the third output to a merger adapter to generate sound event identification data based on the audio data samples.

    CONTEXT-BASED MODEL SELECTION
    6.
    发明申请
    CONTEXT-BASED MODEL SELECTION 有权

    公开(公告)号：US20220164662A1

    公开(公告)日：2022-05-26

    申请号：US17102748

    申请日：2020-11-24

    Applicant: QUALCOMM Incorporated

    Inventor： Fatemeh SAKI ,  Yinyi GUO ,  Erik VISSER

    IPC: G06N3/08 ,  G10L15/183 ,  G10L15/20 ,  G06K9/00 ,  H04W4/02 ,  H04L29/08

    Abstract: A device includes one or more processors configured to receive sensor data from one or more sensor devices. The one or more processors are also configured to determine a context of the device based on the sensor data. The one or more processors are further configured to select a model based on the context. The one or more processors are also configured to process an input signal using the model to generate a context-specific output.

    NOISE SUPPRESSION WEARABLE DEVICE
    8.
    发明申请
    NOISE SUPPRESSION WEARABLE DEVICE 审中-公开

    公开(公告)号：US20200312341A1

    公开(公告)日：2020-10-01

    申请号：US16370812

    申请日：2019-03-29

    Applicant: QUALCOMM Incorporated

    Inventor： Rogerio Guedes ALVES ,  Taher SHAHBAZI MIRZAHASANLOO ,  Erik VISSER ,  Lae-Hoon KIM ,  Fatemeh SAKI ,  Dongmei WANG

    IPC: G10L21/0208 ,  G10L21/02

    Abstract: A device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to perform an active noise cancellation (ANC) operation on noisy input speech as captured by a first microphone, the noisy input speech as captured by a second microphone, or both, to suppress a noise level associated with the noisy input speech. The one or more processors are configured to match a second frequency spectrum of a second signal with a first frequency spectrum of a first signal. The first signal is representative of the noisy input speech as captured by the first microphone, and the second signal is representative of the noisy input speech as captured by the second microphone. The one or more processors are also configured to generate an output speech signal that is representative of input speech based on the second signal.

Patent Agency Ranking