中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

22 records (took 0.016 seconds)

    Feedback Service
    2.
    发明申请
    Feedback Service 有权
    反馈服务

    公开(公告)号：US20150149315A1

    公开(公告)日：2015-05-28

    申请号：US14091871

    申请日：2013-11-27

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Steven Neil Tischer ,  Ari Craine

    IPC: G06Q30/06 ,  G06Q50/00

    CPC classification number: G06Q30/0601 ,  G06Q30/0643 ,  G06Q50/01

    Abstract: Concepts and technologies are disclosed herein for providing and interacting with a feedback service. A processor such as a computing system or a server computer can execute a feedback service. The feedback service can detect activity associated with an item at a user device. The item can an item for sale and the activity can relate to a purchase of the item. The feedback service can generate a social networking post relating to the item. The social networking post can include a visual representation of the item and a solicitation for feedback from a social network. The feedback service can feedback relating to the social networking post. The feedback can include an opinion relating to the item and demographic information relating to an entity that provided the opinion. The feedback service can provide the feedback to the user device and/or other entities.

    Abstract translation: 这里公开了用于提供和与反馈服务交互的概念和技术。 诸如计算系统或服务器计算机的处理器可以执行反馈服务​​。 反馈服务可以检测与用户设备上的项目相关联的活动。 该物品可以出售物品，该活动可以与购买该物品有关。 反馈服务可以产生与该项目相关的社交网络帖子。 社交网络帖子可以包括项目的视觉表示和来自社交网络的反馈的征集。 反馈服务可以反馈与社交网站相关的信息。 反馈可以包括与提供意见的实体有关的项目和人口信息的意见。 反馈服务可以向用户设备和/或其他实体提供反馈。

    System and method for standardized speech recognition infrastructure
    3.
    发明授权
    System and method for standardized speech recognition infrastructure 有权

    公开(公告)号：US08532992B2

    公开(公告)日：2013-09-10

    申请号：US13762978

    申请日：2013-02-08

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Andrej Ljolje ,  Bernard S. Renger ,  Steven Neil Tischer

    IPC: G10L15/06

    CPC classification number: G10L15/075 ,  G10L15/063 ,  G10L15/065 ,  G10L15/07 ,  G10L15/08

    Abstract: Disclosed herein are systems, methods, and computer-readable storage media for selecting a speech recognition model in a standardized speech recognition infrastructure. The system receives speech from a user, and if a user-specific supervised speech model associated with the user is available, retrieves the supervised speech model. If the user-specific supervised speech model is unavailable and if an unsupervised speech model is available, the system retrieves the unsupervised speech model. If the user-specific supervised speech model and the unsupervised speech model are unavailable, the system retrieves a generic speech model associated with the user. Next the system recognizes the received speech from the user with the retrieved model. In one embodiment, the system trains a speech recognition model in a standardized speech recognition infrastructure. In another embodiment, the system handshakes with a remote application in a standardized speech recognition infrastructure.

    Multi-mode IVR
    4.
    发明授权
    Multi-mode IVR 有权
    多模式IVR

    公开(公告)号：US08699673B2

    公开(公告)日：2014-04-15

    申请号：US13871263

    申请日：2013-04-26

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Steven Neil Tischer ,  Robert J. Starr

    IPC: H04M1/64

    CPC classification number: H04M3/493 ,  G06F17/30961

    Abstract: An interface prompts a user to enter a marker during a communications session, in which the user is able to later provide a subsequent version of the marker. Initially, a first version of the marker is received from the user. A processor associates the first version of the marker received from the user with a particular position in an information tree and stores the particular position in the information tree associated with the first version of the marker. A second version of the marker is received from the user and in response, the user is returned to the particular position in the information tree that has been stored and associated with the first version of the marker received from the user.

    Abstract translation: 接口提示用户在通信会话期间输入标记，其中用户稍后可以提供标记的后续版本。 最初，从用户接收标记的第一版本。 处理器将从用户接收的标记的第一版本与信息树中的特定位置相关联，并将特定位置存储在与标记的第一版本相关联的信息树中。 从用户接收标记的第二版本，作为响应，将用户返回到已经存储并与从用户接收的标记的第一版本相关联的信息树中的特定位置。

    SYSTEM AND METHOD FOR STANDARDIZED SPEECH RECOGNITION INFRASTRUCTURE
    8.
    发明申请
    SYSTEM AND METHOD FOR STANDARDIZED SPEECH RECOGNITION INFRASTRUCTURE 有权
    用于标准化语音识别基础结构的系统和方法

    公开(公告)号：US20140006024A1

    公开(公告)日：2014-01-02

    申请号：US14018808

    申请日：2013-09-05

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Andrej Ljolje ,  Bernard S. Renger ,  Steven Neil Tischer

    IPC: G10L15/06

    CPC classification number: G10L15/075 ,  G10L15/063 ,  G10L15/065 ,  G10L15/07 ,  G10L15/08

    Abstract: Disclosed herein are systems, methods, and computer-readable storage media for selecting a speech recognition model in a standardized speech recognition infrastructure. The system receives speech from a user, and if a user-specific supervised speech model associated with the user is available, retrieves the supervised speech model. If the user-specific supervised speech model is unavailable and if an unsupervised speech model is available, the system retrieves the unsupervised speech model. If the user-specific supervised speech model and the unsupervised speech model are unavailable, the system retrieves a generic speech model associated with the user. Next the system recognizes the received speech from the user with the retrieved model. In one embodiment, the system trains a speech recognition model in a standardized speech recognition infrastructure. In another embodiment, the system handshakes with a remote application in a standardized speech recognition infrastructure.

    Abstract translation: 这里公开了用于在标准化语音识别基础设施中选择语音识别模型的系统，方法和计算机可读存储介质。 系统从用户接收语音，并且如果与用户相关联的用户特定的监督语音模型可用，则检索监督的语音模型。 如果用户特定的监督语音模型不可用，并且如果无人监督的语音模型可用，则系统检索无监督语音模型。 如果用户特定的监督语音模型和无监督语音模型不可用，则系统检索与用户相关联的通用语音模型。 接下来，系统使用所检索的模型识别来自用户的接收到的语音。 在一个实施例中，系统在标准化语音识别基础设施中训练语音识别模型。 在另一个实施例中，系统与标准语音识别基础设施中的远程应用握手。

    Automated detection and filtering of audio advertisements
    10.
    发明授权
    Automated detection and filtering of audio advertisements 有权

    公开(公告)号：US10146868B2

    公开(公告)日：2018-12-04

    申请号：US15617256

    申请日：2017-06-08

    Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

    Inventor： Yeon-Jun Kim ,  I. Dan Melamed ,  Bernard S. Renger ,  Steven Neil Tischer

    IPC: G10L25/48 ,  G10L25/78 ,  G10L25/87 ,  G06F17/00 ,  G06F17/30 ,  G10L15/08 ,  G10L25/90

    Abstract: Apparatuses, systems, methods, and media for filtering a data stream are provided. The data stream is partitioned into a plurality of data stream segments. An acoustic parameter is measured in each of the data stream segments. It is determined whether the acoustic parameter satisfies a first predetermined condition. The first predetermined condition includes a number of variances, in which the acoustic parameter exceeds a predetermined variance threshold, exceeding a predetermined number threshold. An extraneous portion of the data stream is identified in which the first predetermined condition is satisfied. It is determined whether the extraneous portion satisfies a second predetermined condition in the data stream. The extraneous portion is deleted from the data stream to produce a filtered data stream in response to the second predetermined condition being satisfied.

Patent Agency Ranking