-
1.发明授权公开(公告)号：US08903712B1
公开(公告)日：2014-12-02
申请号：US13246801
申请日：2011-09-27
申请人： Real Tremblay , Jerome Tremblay , Amy E. Ulug , Jean-Francois Fortier , Francois Berleur , Jeffrey N. Marcus , David Andrew Mauro
发明人： Real Tremblay , Jerome Tremblay , Amy E. Ulug , Jean-Francois Fortier , Francois Berleur , Jeffrey N. Marcus , David Andrew Mauro
IPC分类号： G06F17/28 , G06F17/27 , G06F17/21 , G10L21/00 , G10L25/00 , G06F7/00 , G06F17/30 , G06F17/00 , G06F17/20 , G06F17/22 , G06F17/24 , G06F17/25 , G06F17/26 , G06F3/048 , G06F3/00 , H04M11/00
CPC分类号： G10L15/1815 , G06F3/00 , G06F3/048 , G06F17/2785 , G10L15/1822 , G10L2015/0638 , H04M3/493 , H04M11/00
摘要： A system and method for providing an easy-to-use interface for verifying semantic tags in a steering application in order to generate a natural language grammar. The method includes obtaining user responses to open-ended steering questions, automatically grouping the user responses into groups based on their semantic meaning, and automatically assigning preliminary semantic tags to each of the groups. The user interface enables the user to validate the content of the groups to ensure that all responses within a group have the same semantic meaning and to add or edit semantic tags associated with the groups. The system and method may be applied to interactive voice response (IVR) systems, as well as customer service systems that can communicate with a user via a text or written interface.
摘要翻译： 一种用于提供用于验证转向应用中的语义标签的易于使用的界面以便生成自然语言语法的系统和方法。 该方法包括获取用户对开放式转向问题的响应，根据用户的语义意义将用户响应自动分组，并自动将初步语义标签分配给每个组。 用户界面使用户能够验证组的内容，以确保组内的所有响应具有相同的语义含义，并添加或编辑与组相关联的语义标签。 系统和方法可以应用于交互式语音响应（IVR）系统以及可以经由文本或书写界面与用户通信的客户服务系统。
-
2.发明授权Interface for setting confidence thresholds for automatic speech recognition and call steering applications 有权用于设置自动语音识别和呼叫转向应用的置信阈值的接口公开(公告)号：US08700398B2
公开(公告)日：2014-04-15
申请号：US13305956
申请日：2011-11-29
IPC分类号： G10L15/00
摘要： An interactive user interface is described for setting confidence score thresholds in a language processing system. There is a display of a first system confidence score curve characterizing system recognition performance associated with a high confidence threshold, a first user control for adjusting the high confidence threshold and an associated visual display highlighting a point on the first system confidence score curve representing the selected high confidence threshold, a display of a second system confidence score curve characterizing system recognition performance associated with a low confidence threshold, and a second user control for adjusting the low confidence threshold and an associated visual display highlighting a point on the second system confidence score curve representing the selected low confidence threshold. The operation of the second user control is constrained to require that the low confidence threshold must be less than or equal to the high confidence threshold.
摘要翻译： 描述用于在语言处理系统中设置置信度分数阈值的交互式用户界面。 显示表示与高置信度阈值相关联的系统识别性能的第一系统置信度分数曲线，用于调整高置信度阈值的第一用户控制和突出显示表示所选择的第一系统置信分数曲线上的点的相关联的视觉显示 高置信阈值，表征与低置信度阈值相关联的系统识别性能的第二系统置信度分数曲线的显示，以及用于调整低置信度阈值的第二用户控制和突出显示第二系统置信评分曲线上的点的相关视觉显示 表示所选择的低置信度阈值。 第二用户控制的操作被限制为要求低置信度阈值必须小于或等于高置信度阈值。
-
3.发明申请Method and Apparatus for Setting Selected Recognition Parameters to Minimize an Application Cost Function 有权用于设置所选识别参数以最小化应用成本函数的方法和装置公开(公告)号：US20130204626A1
公开(公告)日：2013-08-08
申请号：US13365587
申请日：2012-02-03
申请人： Jeffrey N. Marcus
发明人： Jeffrey N. Marcus
IPC分类号： G10L11/00
CPC分类号： G10L15/22 , G10L15/1822 , G10L2015/227
摘要： Methods and systems for setting selected automatic speech recognition parameters are described. A data set associated with operation of a speech recognition application is defined and includes: i. recognition states characterizing the semantic progression of a user interaction with the speech recognition application, and ii. recognition outcomes associated with each recognition state. For a selected user interaction with the speech recognition application, an application cost function is defined that characterizes an estimated cost of the user interaction for each recognition outcome. For one or more system performance parameters indirectly related to the user interaction, the parameters are set to values which optimize the cost of the user interaction over the recognition states.
摘要翻译： 描述用于设置所选择的自动语音识别参数的方法和系统。 定义与语音识别应用的操作相关联的数据集，包括：i。 表征用户与语音识别应用交互的语义进展的识别状态，以及ii。 与每个识别状态相关的识别结果。 对于所选用户与语音识别应用的交互，定义了表征每个识别结果的用户交互的估计成本的应用成本函数。 对于与用户交互间接相关的一个或多个系统性能参数，将参数设置为优化用户在识别状态上的交互成本的值。
-
4.发明申请Interface for Setting Confidence Thresholds for Automatic Speech Recognition and Call Steering Applications 有权用于设置自动语音识别和呼叫转向应用的置信度阈值的接口公开(公告)号：US20130138439A1
公开(公告)日：2013-05-30
申请号：US13305956
申请日：2011-11-29
IPC分类号： G10L15/00
摘要： An interactive user interface is described for setting confidence score thresholds in a language processing system. There is a display of a first system confidence score curve characterizing system recognition performance associated with a high confidence threshold, a first user control for adjusting the high confidence threshold and an associated visual display highlighting a point on the first system confidence score curve representing the selected high confidence threshold, a display of a second system confidence score curve characterizing system recognition performance associated with a low confidence threshold, and a second user control for adjusting the low confidence threshold and an associated visual display highlighting a point on the second system confidence score curve representing the selected low confidence threshold. The operation of the second user control is constrained to require that the low confidence threshold must be less than or equal to the high confidence threshold.
摘要翻译： 描述用于在语言处理系统中设置置信度分数阈值的交互式用户界面。 显示表示与高置信度阈值相关联的系统识别性能的第一系统置信度分数曲线，用于调整高置信度阈值的第一用户控制和突出显示表示所选择的第一系统置信分数曲线上的点的相关联的视觉显示 高置信阈值，表征与低置信度阈值相关联的系统识别性能的第二系统置信度分数曲线的显示，以及用于调整低置信度阈值的第二用户控制和突出显示第二系统置信评分曲线上的点的相关视觉显示 表示所选择的低置信度阈值。 第二用户控制的操作被限制为要求低置信阈值必须小于或等于高置信度阈值。
-
5.发明授权Method and apparatus for setting selected recognition parameters to minimize an application cost function 有权用于设置所选识别参数以最小化应用成本函数的方法和装置公开(公告)号：US09177552B2
公开(公告)日：2015-11-03
申请号：US13365587
申请日：2012-02-03
申请人： Jeffrey N. Marcus
发明人： Jeffrey N. Marcus
CPC分类号： G10L15/22 , G10L15/1822 , G10L2015/227
摘要： Methods and systems for setting selected automatic speech recognition parameters are described. A data set associated with operation of a speech recognition application is defined and includes: i. recognition states characterizing the semantic progression of a user interaction with the speech recognition application, and ii. recognition outcomes associated with each recognition state. For a selected user interaction with the speech recognition application, an application cost function is defined that characterizes an estimated cost of the user interaction for each recognition outcome. For one or more system performance parameters indirectly related to the user interaction, the parameters are set to values which optimize the cost of the user interaction over the recognition states.
摘要翻译： 描述用于设置所选择的自动语音识别参数的方法和系统。 定义与语音识别应用的操作相关联的数据集，包括：i。 表征用户与语音识别应用交互的语义进展的识别状态，以及ii。 与每个识别状态相关的识别结果。 对于所选用户与语音识别应用的交互，定义了表征每个识别结果的用户交互的估计成本的应用成本函数。 对于与用户交互间接相关的一个或多个系统性能参数，将参数设置为优化用户在识别状态上的交互成本的值。
-
公开(公告)号：US07844465B2
公开(公告)日：2010-11-30
申请号：US10999773
申请日：2004-11-30
申请人： Jeffrey N Marcus
发明人： Jeffrey N Marcus
CPC分类号： G10L15/08
摘要： Method and system are provided for performing random confirmation in a speech system. When a speech recognition result is received with an associated confidence score indicating a level of confidence with respect to the speech recognition result, a confirmation decision is made in terms of whether a confirmation is to be carried out based on the confidence score. The confirmation decision may be made in a random confirmation mode. A confirmation may be performed when the confirmation decision is to carry out a confirmation on the speech recognition result.
-
公开(公告)号：US20140195329A1
公开(公告)日：2014-07-10
申请号：US14078341
申请日：2013-11-12
IPC分类号： G06Q30/02
CPC分类号： G06Q30/0275 , G06Q30/0242 , G06Q30/0277
摘要： Systems, methods, and media for presenting an advertisement are provided. In some embodiments, systems for presenting an advertisement are provided, the systems comprising: at least one hardware processor that: receives information relating to an advertisement space; determines at least one score for each of a plurality of segments for a potential advertisement for the advertisement space; selects a segment from the plurality of segments for the advertisement space based on the at least one score for the plurality of segments; selects an advertisement for the segment selected; and causes the advertisement to be presented in the advertisement space.
摘要翻译： 提供用于呈现广告的系统，方法和媒体。 在一些实施例中，提供了用于呈现广告的系统，所述系统包括：至少一个硬件处理器，其接收与广告空间有关的信息; 为广告空间的潜在广告确定多个片段中的每一个的至少一个分数; 基于所述多个段的所述至少一个得分，为所述广告空间的所述多个段选择段; 选择所选段的广告; 并使广告呈现在广告空间中。
-
公开(公告)号：US07788103B2
公开(公告)日：2010-08-31
申请号：US10683017
申请日：2004-10-18
申请人： Jeffrey N Marcus
发明人： Jeffrey N Marcus
IPC分类号： G10L21/00
摘要： Method and system are provided for performing random confirmation in a speech system. When a speech recognition result is received with an associated confidence score indicating a level of confidence with respect to the speech recognition result, a confirmation decision is made in terms of whether a confirmation is to be carried out based on the confidence score. The confirmation decision may be made in a random confirmation mode. A confirmation may be performed when the confirmation decision is to carry out a confirmation on the speech recognition result.
摘要翻译： 提供了用于在语音系统中执行随机确认的方法和系统。 当接收到具有指示相对于语音识别结果的置信水平的相关置信度分数的语音识别结果时，根据是否基于置信度得分进行确认来进行确认判定。 可以以随机确认模式进行确认判定。 当确认决定要对语音识别结果进行确认时，可以进行确认。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.016 秒)