知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

3946 条记录 (耗时 0.033 秒)

    Emergency communication system with contextual snippets
    44.
    发明授权
    Emergency communication system with contextual snippets 有权

    公开(公告)号：US11825020B2

    公开(公告)日：2023-11-21

    申请号：US17432056

    申请日：2020-12-22

    申请人： Axon Enterprise, Inc.

    发明人： Anshuman Srivastava ,  Michael Bauer ,  Joseph Pepper

    IPC分类号： G10L19/02 ,  H04M3/51 ,  H04M3/42

    CPC分类号： H04M3/5116 ,  H04M3/42221 ,  H04M2203/553

    摘要： Systems and methods for processing emergency communications are provided. A system may receive an emergency communication initiated by an emergency communicator. The system may detect a data field action in response to an emergency receiver entering a data input based on the emergency communication. The system may capture a timestamp of when the data field action occurred. The system may generate a communication snippet based on the action timestamp and a snippet length. The communication snippet may be configured to provide context from the emergency communication to the data input. The system may transmit the communication snippet and the data input to an emergency responder.

    SPEECH CODING USING AUTO-REGRESSIVE GENERATIVE NEURAL NETWORKS
    45.
    发明公开
    SPEECH CODING USING AUTO-REGRESSIVE GENERATIVE NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230368804A1

    公开(公告)日：2023-11-16

    申请号：US18144413

    申请日：2023-05-08

    申请人： Google LLC

    发明人： Willem Bastiaan Kleijn ,  Jan K. Skoglund ,  Alejandro Luebs ,  Sze Chie Lim

    IPC分类号： G10L19/02 ,  G10L25/30

    CPC分类号： G10L19/0204 ,  G10L25/30

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for coding speech using neural networks. One of the methods includes obtaining a bitstream of parametric coder parameters characterizing spoken speech; generating, from the parametric coder parameters, a conditioning sequence; generating a reconstruction of the spoken speech that includes a respective speech sample at each of a plurality of decoder time steps, comprising, at each decoder time step: processing a current reconstruction sequence using an auto-regressive generative neural network, wherein the auto-regressive generative neural network is configured to process the current reconstruction to compute a score distribution over possible speech sample values, and wherein the processing comprises conditioning the auto-regressive generative neural network on at least a portion of the conditioning sequence; and sampling a speech sample from the possible speech sample values.

    SYSTEM MONITORING BY PLAYING SOUND
    49.
    发明公开
    SYSTEM MONITORING BY PLAYING SOUND 审中-公开

    公开(公告)号：US20230326471A1

    公开(公告)日：2023-10-12

    申请号：US17658094

    申请日：2022-04-06

    申请人： International Business Machines Corporation

    发明人： Albert Alexander Chung

    IPC分类号： G10L19/02 ,  G10L19/08 ,  G10L19/005

    CPC分类号： G10L19/0212 ,  G10L19/08 ,  G10L19/005

    摘要： A computer-implemented method, a computer program product, and a computer system for system monitoring. A computer system convert a time domain representation of first sound into a frequency domain representation, maps monitoring datasets of a monitored system to frequencies in the frequency domain representation, modifies the amplitudes of the respective frequencies according mapping rules defined by a user, convert the frequency domain representation into the time domain representation and generate a sound wave in a digital format which has modified amplitudes, converts the sound wave in the digital format to a sound wave in an analog format, and feeds the sound wave in the analog format to a sound system to play second sound. Performance of the monitored system is monitored by the user listening to the second sound and comparing the first and second sound.