知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

296 条记录 (耗时 0.028 秒)

    METHODS AND SYSTEMS FOR AUTOMATIC DISCOVERY OF FRAUDULENT CALLS USING SPEAKER RECOGNITION
    2.
    发明公开
    METHODS AND SYSTEMS FOR AUTOMATIC DISCOVERY OF FRAUDULENT CALLS USING SPEAKER RECOGNITION 审中-公开

    公开(公告)号：US20240195905A1

    公开(公告)日：2024-06-13

    申请号：US18581804

    申请日：2024-02-20

    申请人： Capital One Services, LLC

    发明人： Zhiyuan GUAN ,  Carl S. ASHBY ,  Isabelle Alice Yvonne MOULINIER ,  Mark E. DICKISON

    IPC分类号： H04M1/67 ,  G10L17/00 ,  H04M3/38

    CPC分类号： H04M1/67 ,  G10L17/00 ,  H04M3/385 ,  H04M2201/41

    摘要： A method for determining potentially undesirable voices, in embodiments, includes: receiving audio recordings comprising voices associated with undesirable activity, and determining audio components of each of the audio recordings. The method may further comprise generating a multi-dimensional vector of the audio components for each of the plurality of audio recordings, and comparing audio components between the multi-dimensional vectors to determine clusters of multi-dimensional vectors, each cluster comprising two or more of the multi-dimensional vectors of audio components, wherein each cluster corresponds to a blacklisted voice. The method may further comprise receiving an audio recording or audio stream, and determining whether the audio recording or audio stream is associated with a voice associated with undesirable activity based on a comparison to the clusters.

    SECURE VIDEO VISITATION SYSTEM
    3.
    发明公开
    SECURE VIDEO VISITATION SYSTEM 审中-公开

    公开(公告)号：US20240114111A1

    公开(公告)日：2024-04-04

    申请号：US18377119

    申请日：2023-10-05

    申请人： Global Tel*Link Corporation

    发明人： Stephen L. HODGE ,  Anthony BAMBOCCI

    IPC分类号： H04N7/14 ,  G07C9/37 ,  H04L65/1059 ,  H04L65/1069 ,  H04M3/38

    CPC分类号： H04N7/147 ,  G07C9/37 ,  H04L65/1059 ,  H04L65/1069 ,  H04M3/38 ,  H04N7/142 ,  H04M3/382 ,  H04M3/385 ,  H04M2201/50

    摘要： Video conferencing in a controlled environment facility entails significant security concerns. These concerns are even more prevalent in a system that permits residents of such facilities to communicate via their own personal devices. Therefore, in order to alleviate these concerns and provide a secure system in which a resident is able to make video calls using their personal device, a kiosk unit is provided to which the personal device must be linked for completing a video call. When making the video call, the camera and display on the personal device are disabled, and all video data is captured and displayed by the kiosk unit. The link between the kiosk unit and the personal device facilitates the exchange of the image information for transmission to the outside party, or display to the user. By providing a fixed camera, and disabling the personal device camera, security can be maintained while permitting video calling services.

    System and method for multilingual authentication access to communication system in controlled environment
    4.
    发明授权
    System and method for multilingual authentication access to communication system in controlled environment 有权

    公开(公告)号：US09794399B1

    公开(公告)日：2017-10-17

    申请号：US15390296

    申请日：2016-12-23

    申请人： GLOBAL TEL*LINK CORP.

    发明人： Stephen L. Hodge

    IPC分类号： H04M11/00 ,  H04M3/38 ,  H04M3/42

    CPC分类号： H04M3/38 ,  H04M3/385 ,  H04M3/42068 ,  H04M2201/41 ,  H04M2203/6054 ,  H04M2203/6072 ,  H04M2242/12

    摘要： A system and method for multilingual authentication access to a communication system in a controlled environment is disclosed. The system includes a communication subsystem that connects a communication between a first communication device and a second communication device, wherein one of the first communication device or the second communication device is used by the inmate of the correctional system. The system also includes a profile subsystem configured to determine profile information of a party associated with the first communication device. The system further includes an authentication subsystem that provides one or more challenge questions to the first communication device based on the profile information, receives at least one response to the one or more challenge questions from the first communication device, and authorizes connection of the communication between the first communication device and the second communication device based on the at least one response.

    DYNAMIC THRESHOLD FOR SPEAKER VERIFICATION
    7.
    发明申请
    DYNAMIC THRESHOLD FOR SPEAKER VERIFICATION 有权

    公开(公告)号：US20170103759A1

    公开(公告)日：2017-04-13

    申请号：US15342388

    申请日：2016-11-03

    申请人： Google Inc.

    发明人： Jakob Nicolaus Foerster ,  Diego Melendo Casado

    IPC分类号： G10L17/20 ,  G10L25/84 ,  G10L17/06 ,  G10L17/24 ,  G10L17/02

    CPC分类号： G10L17/20 ,  G06F3/167 ,  G10L17/005 ,  G10L17/02 ,  G10L17/04 ,  G10L17/06 ,  G10L17/08 ,  G10L17/12 ,  G10L17/22 ,  G10L17/24 ,  G10L25/84 ,  H04M3/385

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a dynamic threshold for speaker verification are disclosed. In one aspect, a method includes the actions of receiving, for each of multiple utterances of a hotword, a data set including at least a speaker verification confidence score, and environmental context data. The actions further include selecting from among the data sets, a subset of the data sets that are associated with a particular environmental context. The actions further include selecting a particular data set from among the subset of data sets based on one or more selection criteria. The actions further include selecting, as a speaker verification threshold for the particular environmental context, the speaker verification confidence score. The actions further include providing the speaker verification threshold for use in performing speaker verification of utterances that are associated with the particular environmental context.

    Dynamic threshold for speaker verification
    9.
    发明授权
    Dynamic threshold for speaker verification 有权
    讲话者验证的动态阈值

    公开(公告)号：US09502039B2

    公开(公告)日：2016-11-22

    申请号：US15188047

    申请日：2016-06-21

    申请人： Google Inc.

    发明人： Jakob Nicolaus Foerster ,  Diego Melendo Casado

    IPC分类号： G10L17/00 ,  G10L15/00 ,  G10L25/00 ,  G10L17/20 ,  G10L17/24 ,  G06F3/16 ,  G10L17/02 ,  H04M3/38 ,  G10L17/12

    CPC分类号： G10L17/20 ,  G06F3/167 ,  G10L17/005 ,  G10L17/02 ,  G10L17/04 ,  G10L17/06 ,  G10L17/08 ,  G10L17/12 ,  G10L17/22 ,  G10L17/24 ,  G10L25/84 ,  H04M3/385

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a dynamic threshold for speaker verification are disclosed. In one aspect, a method includes the actions of receiving, for each of multiple utterances of a hotword, a data set including at least a speaker verification confidence score, and environmental context data. The actions further include selecting from among the data sets, a subset of the data sets that are associated with a particular environmental context. The actions further include selecting a particular data set from among the subset of data sets based on one or more selection criteria. The actions further include selecting, as a speaker verification threshold for the particular environmental context, the speaker verification confidence score. The actions further include providing the speaker verification threshold for use in performing speaker verification of utterances that are associated with the particular environmental context.

    摘要翻译： 公开了用于说话人验证的动态阈值的方法，系统和装置，包括在计算机存储介质上编码的计算机程序。 一方面，一种方法包括针对热词的多个话语中的每一个接收包括至少说话人验证置信度得分和环境上下文数据的数据集的动作。 动作还包括从数据集中选择与特定环境上下文相关联的数据集的子集。 动作还包括基于一个或多个选择标准从数据集的子集中选择特定数据集。 该动作进一步包括作为特定环境背景的说话者验证阈值来选择说话者验证置信度得分。 该动作进一步包括提供说话者验证阈值，以用于执行与特定环境背景相关联的话语的说话者验证。