中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

56 records (took 0.057 seconds)

    SYSTEMS AND METHODS FOR EXTRACTING HEADSHOTS FROM IMAGES
    33.
    发明申请
    SYSTEMS AND METHODS FOR EXTRACTING HEADSHOTS FROM IMAGES 有权

    公开(公告)号：US20220277458A1

    公开(公告)日：2022-09-01

    申请号：US17648292

    申请日：2022-01-18

    Applicant: PROMPTU SYSTEMS CORPORATION

    Inventor： James Henry NEALAND ,  Blair William Thomas FIDLER

    IPC: G06T7/11 ,  G06V40/16

    Abstract: Various embodiments contemplate systems, architectures and methods for extracting and selecting headshots of human or non-human entities from catalogs of images of such subjects. The methods described may find and extract faces from within groups of subjects, verify that the extracted faces correspond to the desired subject, determine cropping or masking regions, or both, of rectangular, circular, elliptical or some other geometry to provide an easily recognized image of the desired subject, expand the output image by synthesizing pixels as may be needed for a desired cropping or masking region, select preferred images among a collection of images of the desired subject, and perform other useful functions. The resulting output images may be in either direct form, reference form or both forms.

    SYSTEMS AND METHODS FOR ADAPTIVE PROPER NAME ENTITY RECOGNITION AND UNDERSTANDING
    34.
    发明申请
    SYSTEMS AND METHODS FOR ADAPTIVE PROPER NAME ENTITY RECOGNITION AND UNDERSTANDING 有权

    公开(公告)号：US20210383805A1

    公开(公告)日：2021-12-09

    申请号：US17303325

    申请日：2021-05-26

    Applicant: Promptu Systems Corporation

    Inventor： Harry William Printz

    IPC: G10L15/22 ,  G10L15/18 ,  G10L15/02 ,  G10L15/16 ,  G10L15/19 ,  G01C21/36 ,  G10L15/32 ,  G06F40/295

    Abstract: Various embodiments contemplate systems and methods for performing automatic speech recognition (ASR) and natural language understanding (NLU) that enable high accuracy recognition and understanding of freely spoken utterances which may contain proper names and similar entities. The proper name entities may contain or be comprised wholly of words that are not present in the vocabularies of these systems as normally constituted. Recognition of the other words in the utterances in question, e.g. words that are not part of the proper name entities, may occur at regular, high recognition accuracy. Various embodiments provide as output not only accurately transcribed running text of the complete utterance, but also a symbolic representation of the meaning of the input, including appropriate symbolic representations of proper name entities, adequate to allow a computer system to respond appropriately to the spoken request without further analysis of the user's input.

    Systems and methods for adaptive proper name entity recognition and understanding
    35.
    发明授权
    Systems and methods for adaptive proper name entity recognition and understanding 有权

    公开(公告)号：US11024308B2

    公开(公告)日：2021-06-01

    申请号：US16229196

    申请日：2018-12-21

    Applicant: Promptu Systems Corporation

    Inventor： Harry William Printz

    IPC: G10L15/22 ,  G10L15/18 ,  G10L15/02 ,  G10L15/16 ,  G10L15/19 ,  G01C21/36 ,  G10L15/32 ,  G06F40/295 ,  G06F3/16

    Abstract: Various embodiments contemplate systems and methods for performing automatic speech recognition (ASR) and natural language understanding (NLU) that enable high accuracy recognition and understanding of freely spoken utterances which may contain proper names and similar entities. The proper name entities may contain or be comprised wholly of words that are not present in the vocabularies of these systems as normally constituted. Recognition of the other words in the utterances in question, e.g. words that are not part of the proper name entities, may occur at regular, high recognition accuracy. Various embodiments provide as output not only accurately transcribed running text of the complete utterance, but also a symbolic representation of the meaning of the input, including appropriate symbolic representations of proper name entities, adequate to allow a computer system to respond appropriately to the spoken request without further analysis of the user's input.

    Systems and methods for adaptive proper name entity recognition and understanding
    37.
    发明授权
    Systems and methods for adaptive proper name entity recognition and understanding 有权
    适应适当名称实体识别和理解的系统和方法

    公开(公告)号：US09449599B2

    公开(公告)日：2016-09-20

    申请号：US14292800

    申请日：2014-05-30

    Applicant: Promptu Systems Corporation

    Inventor： Harry William Printz

    IPC: G10L15/00 ,  G10L15/19 ,  G10L15/32 ,  G06F17/27 ,  G10L15/22

    CPC classification number: G10L15/19 ,  G06F17/278 ,  G10L15/32 ,  G10L2015/228

    Abstract: Various embodiments contemplate systems and methods for performing automatic speech recognition (ASR) and natural language understanding (NLU) that enable high accuracy recognition and understanding of freely spoken utterances which may contain proper names and similar entities. The proper name entities may contain or be comprised wholly of words that are not present in the vocabularies of these systems as normally constituted. Recognition of the other words in the utterances in question—e.g., words that are not part of the proper name entities—may occur at regular, high recognition accuracy. Various embodiments provide as output not only accurately transcribed running text of the complete utterance, but also a symbolic representation of the meaning of the input, including appropriate symbolic representations of proper name entities, adequate to allow a computer system to respond appropriately to the spoken request without further analysis of the user's input.

    Abstract translation: 各种实施例考虑用于执行自动语音识别（ASR）和自然语言理解（NLU）的系统和方法，其使得能够高度准确地识别和理解可能包含适当名称和类似实体的自由说话话语。 正确的名称实体可以包含或完全由通常构成的这些系统的词汇中不存在的单词组成。 识别所讨论的话语中的其他单词 - 例如，不属于正确名称实体的单词 - 可能会以正常，高识别精度发生。 各种实施例提供的输出不仅准确地转录了完整话语的运行文本，还提供了输入意义的符号表示，包括合适的名称实体的合适的符号表示，足以允许计算机系统适当地响应于口头请求 无需进一步分析用户的输入。

    Efficient empirical determination, computation, and use of acoustic confusability measures
    38.
    发明授权
    Efficient empirical determination, computation, and use of acoustic confusability measures 有权
    有效的经验确定，计算和使用声学混淆度量

    公开(公告)号：US08959019B2

    公开(公告)日：2015-02-17

    申请号：US11932122

    申请日：2007-10-31

    Applicant: Harry Printz ,  Narren Chittar

    Inventor： Harry Printz ,  Narren Chittar

    IPC: G10L15/06 ,  G10L15/08 ,  G10L17/26 ,  G06Q30/02 ,  G06F17/30

    CPC classification number: G10L15/187 ,  G06F17/30861 ,  G06F17/30867 ,  G06Q30/02 ,  G10L15/02 ,  G10L15/142 ,  G10L15/18 ,  G10L15/22 ,  G10L17/26 ,  G10L2015/025

    Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

    Abstract translation: 声学混淆度测量的有效经验确定，计算和使用包括：（1）经验导出的声学混淆度量度，包括用于确定给定语言中的任何两个文本短语之间的声学​​混淆性的装置，其中声学混淆度的度量是 经验地衍生自应用特定语音识别技术的示例，其中该过程不需要访问语音识别技术的内部计算模型，并且不依赖于任何特定的内部结构或建模技术，并且其中过程是 基于初步估计的迭代改进; （2）用于有效计算经验导出的声学混淆度测量的技术，包括有效应用声学混淆评分的手段，允许实际应用于非常大规模的问题; 和（3）使用声学混淆度量的方法，对哪些特定短语进行原则性的选择，使语音识别应用程序可识别。

    Automatic service vehicle hailing and dispatch system and method
    39.
    发明授权
    Automatic service vehicle hailing and dispatch system and method 有权
    自动售后服务车辆调度系统及方法

    公开(公告)号：US08565789B2

    公开(公告)日：2013-10-22

    申请号：US13168685

    申请日：2011-06-24

    Applicant: Giuseppe Staffaroni ,  Matteo Monteverdi ,  John A. Lynch ,  Harry W. Printz

    Inventor： Giuseppe Staffaroni ,  Matteo Monteverdi ,  John A. Lynch ,  Harry W. Printz

    IPC: H04W24/00

    CPC classification number: G06Q10/08 ,  G06Q10/06311 ,  G10L15/26

    Abstract: A system and method are provided for improving efficiency of operation and convenience of access to a fleet of taxis, or other service vehicles, requiring rapid, on-demand dispatch to customer-determined locations. Automatic speech recognition (ASR) and/or radiolocation technology are used to automate the entry of the customer pickup location, and optionally the dropoff location and other relevant information as well. A customer speaks the pickup location into a cellular telephone which then digitizes and transmits it as a data communication to an ASR system. The ASR system decodes the digitized utterance into a pickup location which is passed to a vehicle matching and dispatch system. The vehicle matching and dispatch system matches a taxi and dispatches it to the pickup location. In one embodiment, the identified pickup location is transmitted to the customer's cellular telephone for confirmation or correction, before dispatch of the requested taxi.

    Abstract translation: 提供了一种系统和方法，用于提高运营效率和方便访问出租车或其他服务车辆，要求快速按需派遣到客户确定的位置。 自动语音识别（ASR）和/或无线电定位技术用于自动化客户接收位置的输入，以及可选择的丢弃位置和其他相关信息。 客户将拾音器位置传送到蜂窝电话中，然后数字化并将其作为数据通信发送到ASR系统。 ASR系统将数字化话音解码为传送到车辆匹配和调度系统的拾取位置。 车辆匹配和调度系统匹配出租车并将其发送到接收位置。 在一个实施例中，在发送所请求的出租车之前，将所识别的拾取位置发送到客户的蜂窝电话以进行确认或更正。

Patent Agency Ranking