知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

74 条记录 (耗时 0.016 秒)

    Device and method for stereo noise cancellation
    41.
    发明授权
    Device and method for stereo noise cancellation 有权

    公开(公告)号：US11094333B2

    公开(公告)日：2021-08-17

    申请号：US16586983

    申请日：2019-09-28

    申请人： Sogang University Research & Business Development Foundation

    发明人： Hyung Min Park ,  Byung Joon Cho

    IPC分类号： G10L21/02 ,  G10L21/0216 ,  G10L21/0208 ,  G10L21/0264 ,  G10L21/0232 ,  G10L25/06 ,  H04B3/23 ,  H04M9/08 ,  H04R5/04 ,  H04R3/04

    摘要： A method of noise cancellation comprises providing a first estimated output signal based on an input signal and a first prior far-end channel filter and a second prior far-end channel filter corresponding to a prior frame, updating a first current far-end channel filter corresponding to a current frame according to the first estimated output signal and the first prior far-end channel filter, providing a second estimated output signal based on the input signal, the first current far-end channel filter, and the second prior far-end channel filter, updating a second current far-end channel filter corresponding to the current frame according to the second estimated output signal and the second prior far-end channel filter, and providing a resultant signal based on the input signal, the first current far-end channel filter, and the second current far-end channel filter.

    Apparatus and process for synthesizing natural gas using carbon dioxide and water in air
    42.
    发明授权
    Apparatus and process for synthesizing natural gas using carbon dioxide and water in air 有权

    公开(公告)号：US10815442B2

    公开(公告)日：2020-10-27

    申请号：US16460071

    申请日：2019-07-02

    申请人： Sogang University Research & Business Development Foundation

    发明人： Kyung Byung Yoon

    IPC分类号： C10L3/08 ,  B01D53/22 ,  B01D53/26 ,  B01J19/00 ,  B01J19/24 ,  C07C1/04 ,  C25B1/04 ,  F25J3/04 ,  B01D53/02 ,  B01J19/08

    摘要： An apparatus for producing a natural gas using carbon dioxide and water in air that includes an air-compressing member, a water collecting member, a water storing member, a carbon dioxide collecting member, a water electrolysis member, and a methanation reaction member. The water electrolysis member electrolyzes water separated from compressed air. The methanation reaction member generates a natural gas by reacting hydrogen from the electrolysis and carbon dioxide from the carbon dioxide collecting member. A method of producing a natural gas using carbon dioxide and water in air includes supplying hydrogen electrolyzed from water separated from air and carbon dioxide collected from the dry air to a methanation reaction member to generate a natural gas. A natural gas-synthesizing equipment system includes an apparatus for producing a natural gas using carbon dioxide and water in air.

    METHOD OF DETECTING A TRANSCRIPTION ERROR IN SPEECH RECOGNITION CORPUS AND DEVICE FOR THE SAME
    43.
    发明公开
    METHOD OF DETECTING A TRANSCRIPTION ERROR IN SPEECH RECOGNITION CORPUS AND DEVICE FOR THE SAME 审中-公开

    公开(公告)号：US20240194203A1

    公开(公告)日：2024-06-13

    申请号：US18532770

    申请日：2023-12-07

    申请人： SOGANG UNIVERSITY RESEARCH & BUSINESS DEVELOPMENT FOUNDATION

    发明人： Myoung Wan KOO ,  Jeong Pil LEE

    IPC分类号： G10L15/26 ,  G10L15/01 ,  G10L15/22

    CPC分类号： G10L15/26 ,  G10L15/01 ,  G10L15/22

    摘要： Provided are a method and device for detecting transcription error in a speech recognition corpus. The method of detecting a transcription error in speech recognition corpus includes following steps: (a) receiving the speech recognition corpus including a speech file and a text label for the speech file; (b) performing speech recognition on the speech file of the speech recognition corpus using a speech recognition model and converting the speech recognition result into text; (c) extracting a performance evaluation index of the speech recognition model; (d) extracting a PPL(s2) for the text label and a PPL(s1) for the text using a language model; and (e) detecting a transcription error in text label of the speech recognition corpus using the extracted performance evaluation index and the PPL(s2) and PPL(s1).