中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.013 seconds)

    VOICE COMMAND MASKING SYSTEMS AND METHODS
    1.
    发明申请
    VOICE COMMAND MASKING SYSTEMS AND METHODS 审中-公开

    公开(公告)号：US20190103098A1

    公开(公告)日：2019-04-04

    申请号：US15720446

    申请日：2017-09-29

    Applicant: INTEL CORPORATION

    Inventor： Sean J.W. Lawrence ,  Devon Worrell ,  Michael E. Deisher

    IPC: G10L15/22 ,  G10L15/20 ,  G10K11/175

    CPC classification number: G10L15/22 ,  G06F3/167 ,  G10K11/175 ,  G10L15/08 ,  G10L15/20 ,  G10L21/003 ,  G10L2015/088 ,  G10L2015/223 ,  G10L2021/02087 ,  H04K1/00

    Abstract: Techniques are disclosed for reliably masking speech commands directed to one or more computing devices to prevent the speech commands from being rendered. In some embodiments, each of the one or more computing devices includes components configured to generate acoustic data from ambient sound waves, process the acoustic data to identify a speech command sequence, and mask the speech command sequence from being rendered. At least some of the systems and methods disclosed herein monitor inbound audio at a fine grain level of detail. Working at this level of granularity enables the system and methods described herein to detect potential speech commands early within the user's utterance thereof and to discriminate quickly between true speech commands and other user utterances. These early detection and discrimination features, in turn, enable some embodiments to manage potential communication disruptions (e.g., jitter and/or latency) by modifying rates of audio prior to rendering.

    Dynamic quantization of neural networks
    2.
    发明授权
    Dynamic quantization of neural networks 有权

    公开(公告)号：US12282852B2

    公开(公告)日：2025-04-22

    申请号：US18363408

    申请日：2023-08-01

    Applicant: Intel Corporation

    Inventor： Michael E. Deisher

    IPC: G06N3/08 ,  G06F5/01 ,  G06F7/02 ,  G06F7/544 ,  G06F7/57 ,  G06N3/02 ,  G06N3/044 ,  G06N3/045 ,  G06N3/048 ,  G06N3/063

    Abstract: An apparatus for applying dynamic quantization of a neural network is described herein. The apparatus includes a scaling unit and a quantizing unit. The scaling unit is to calculate an initial desired scale factors of a plurality of inputs, weights and a bias and apply the input scale factor to a summation node. Also, the scaling unit is to determine a scale factor for a multiplication node based on the desired scale factors of the inputs and select a scale factor for an activation function and an output node. The quantizing unit is to dynamically requantize the neural network by traversing a graph of the neural network.

    DYNAMIC QUANTIZATION OF NEURAL NETWORKS
    6.
    发明申请
    DYNAMIC QUANTIZATION OF NEURAL NETWORKS 审中-公开

    公开(公告)号：US20190042935A1

    公开(公告)日：2019-02-07

    申请号：US15857438

    申请日：2017-12-28

    Applicant: Intel Corporation

    Inventor： Michael E. Deisher

    IPC: G06N3/08 ,  G06F7/57

    Abstract: An apparatus for applying dynamic quantization of a neural network is described herein. The apparatus includes a scaling unit and a quantizing unit. The scaling unit is to calculate an initial desired scale factors of a plurality of inputs, weights and a bias and apply the input scale factor to a summation node. Also, the scaling unit is to determine a scale factor for a multiplication node based on the desired scale factors of the inputs and select a scale factor for an activation function and an output node. The quantizing unit is to dynamically requantize the neural network by traversing a graph of the neural network.

    Voice command masking systems and methods
    9.
    发明授权
    Voice command masking systems and methods 有权

    公开(公告)号：US10424299B2

    公开(公告)日：2019-09-24

    申请号：US15720446

    申请日：2017-09-29

    Applicant: INTEL CORPORATION

    Inventor： Sean J. W. Lawrence ,  Devon Worrell ,  Michael E. Deisher

    IPC: G10L15/20 ,  G10L15/22 ,  G06F3/00 ,  G10K11/175 ,  G06F3/16 ,  G10L15/08 ,  G10L21/003 ,  H04K1/00 ,  G10L21/0208

    Abstract: Techniques are disclosed for reliably masking speech commands directed to one or more computing devices to prevent the speech commands from being rendered. In some embodiments, each of the one or more computing devices includes components configured to generate acoustic data from ambient sound waves, process the acoustic data to identify a speech command sequence, and mask the speech command sequence from being rendered. At least some of the systems and methods disclosed herein monitor inbound audio at a fine grain level of detail. Working at this level of granularity enables the system and methods described herein to detect potential speech commands early within the user's utterance thereof and to discriminate quickly between true speech commands and other user utterances. These early detection and discrimination features, in turn, enable some embodiments to manage potential communication disruptions (e.g., jitter and/or latency) by modifying rates of audio prior to rendering.

Patent Agency Ranking