知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

1391 条记录 (耗时 0.025 秒)

    System and Method for Secure Training of Speech Processing Systems
    5.
    发明公开
    System and Method for Secure Training of Speech Processing Systems 审中-公开

    公开(公告)号：US20230410814A1

    公开(公告)日：2023-12-21

    申请号：US17840795

    申请日：2022-06-15

    申请人： Nuance Communications, Inc.

    发明人： Shou-Chun Yin ,  Junho Park ,  Dushyant Sharma ,  DoYeong Kim

    IPC分类号： G10L15/26 ,  G10L15/06 ,  G10L13/04

    CPC分类号： G10L15/26 ,  G10L15/063 ,  G10L13/04

    摘要： A method, computer program product, and computing system for generating an obscured speech signal from an input speech signal and an obscured transcription from a transcription of the input speech signal. A speaker embedding may be extracted from the input speech signal. A speaker embedding delta may be generated based upon, at least in part, the extracted speaker embedding and a synthetic speaker embedding. A synthetic speech signal may be generated from the obscured speech signal using the synthetic speaker embedding. A residual signal may be generated based upon, at least in part, the obscured speech signal and the speaker embedding delta. A speech processing system may be trained using the obscured transcription, the synthetic speech signal, the speaker embedding delta, and the residual signal.

    DATA AUGMENTATION SYSTEM AND METHOD FOR MULTI-MICROPHONE SYSTEMS
    6.
    发明公开
    DATA AUGMENTATION SYSTEM AND METHOD FOR MULTI-MICROPHONE SYSTEMS 审中-公开

    公开(公告)号：US20230230581A1

    公开(公告)日：2023-07-20

    申请号：US17579786

    申请日：2022-01-20

    申请人： Nuance Communications, Inc.

    发明人： Dushyant Sharma ,  Ljubomir Milanovi ,  Philip Salletmayr ,  Rong Gong ,  Patrick A. Naylor

    IPC分类号： G10L15/08

    CPC分类号： G10L15/08

    摘要： A method, computer program product, and computing system for obtaining one or more speech signals from a first device, thus defining one or more first device speech signals. One or more speech signals may be obtained from a second device, thus defining one or more second device speech signals. One or more noise component models mapping one or more noise components from the one or more first device speech signals to the one or more second device speech signals may be generated. One or more augmented second device speech signals may be generated based upon, at least in part, the one or more noise component models and first device training data.

    Systems and Methods for Queue Call Waiting Deflection
    8.
    发明公开
    Systems and Methods for Queue Call Waiting Deflection 审中-公开

    公开(公告)号：US20230198922A1

    公开(公告)日：2023-06-22

    申请号：US17554743

    申请日：2021-12-17

    申请人： Nuance Communications, Inc.

    发明人： Eduardo Olvera

    IPC分类号： H04L51/046 ,  H04L51/02 ,  H04L67/60

    CPC分类号： H04L51/046 ,  H04L51/02 ,  H04L67/32

    摘要： A method, computer program product, and computer system for placing, by a computing device, a user into a first queue on a first communication channel to converse with a second user. A trigger may be identified for the first communication channel. The user may be sent a self-service option based upon, at least in part, identifying the trigger for the first communication channel, wherein the self-service option is sent on an alternate communication channel while the user is in the first queue.