-
公开(公告)号：US07831424B2
公开(公告)日：2010-11-09
申请号：US12060903
申请日：2008-04-02
CPC分类号： G10L17/02
摘要： A method is presented which reduces data flow and thereby increases processing capacity while preserving a high level of accuracy in a distributed speech processing environment for speaker detection. The method and system of the present invention includes filtering out data based on a target speaker specific subset of labels using data filters. The method preserves accuracy and passes only a fraction of the data by optimizing target specific performance measures. Therefore, a high level of speaker recognition accuracy is maintained while utilizing existing processing capabilities.
摘要翻译： 提出了一种减少数据流并从而增加处理能力的方法，同时在用于说话者检测的分布式语音处理环境中保持高水准的准确性。 本发明的方法和系统包括使用数据滤波器基于目标说话者指定的标签子集过滤掉数据。 该方法保留精度，并通过优化目标特定性能度量仅传递一小部分数据。 因此，在利用现有的处理能力的同时，维持高水平的说话者识别精度。
-
公开(公告)号：US20090043579A1
公开(公告)日：2009-02-12
申请号：US12060903
申请日：2008-04-02
IPC分类号： G10L15/00
CPC分类号： G10L17/02
摘要： A method is presented which reduces data flow and thereby increases processing capacity while preserving a high level of accuracy in a distributed speech processing environment for speaker detection. The method and system of the present invention includes filtering out data based on a target speaker specific subset of labels using data filters. The method preserves accuracy and passes only a fraction of the data by optimizing target specific performance measures. Therefore, a high level of speaker recognition accuracy is maintained while utilizing existing processing capabilities.
摘要翻译： 提出了一种减少数据流并从而增加处理能力的方法，同时在用于说话者检测的分布式语音处理环境中保持高水准的准确性。 本发明的方法和系统包括使用数据滤波器基于目标说话者指定的标签子集过滤掉数据。 该方法保留精度，并通过优化目标特定性能度量仅传递一小部分数据。 因此，在利用现有的处理能力的同时，维持高水平的说话者识别精度。
-
公开(公告)号：US20080010067A1
公开(公告)日：2008-01-10
申请号：US11482408
申请日：2006-07-07
IPC分类号： G10L15/04
CPC分类号： G10L17/02
摘要： A method is presented which reduces data flow and thereby increases processing capacity while preserving a high level of accuracy in a distributed speech processing environment for speaker detection. The method and system of the present invention includes filtering out data based on a target speaker specific subset of labels using data filters. The method preserves accuracy and passes only a fraction of the data by optimizing target specific performance measures. Therefore, a high level of speaker recognition accuracy is maintained while utilizing existing processing capabilities.
摘要翻译： 提出了一种减少数据流并从而增加处理能力的方法，同时在用于说话者检测的分布式语音处理环境中保持高水准的准确性。 本发明的方法和系统包括使用数据滤波器基于目标说话者指定的标签子集过滤掉数据。 该方法保留精度，并通过优化目标特定性能度量仅传递一小部分数据。 因此，在利用现有的处理能力的同时，维持高水平的说话者识别精度。
-
公开(公告)号：US07769583B2
公开(公告)日：2010-08-03
申请号：US11383199
申请日：2006-05-13
CPC分类号： G10L17/06
摘要： A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.
摘要翻译： 一种使用训练数据的统计模型对模拟电信号进行分类的系统，方法和计算机程序产品。 描述了一种技术来以使信号压缩最大化的方式对模拟电信号进行量化，同时最小化对压缩信号进行分类的能力的减小。 这些目标通过利用设计用于最小化对数似然比的功率损失的量化器来实现。 描述了另一种技术，以通过对经过所有维度可用的最大位数的量化特征向量的每个维度最佳地分配位数来增强量化过程。
-
公开(公告)号：US20100191531A1
公开(公告)日：2010-07-29
申请号：US12753859
申请日：2010-04-03
IPC分类号： G10L15/28
CPC分类号： G10L17/06
摘要： A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.
摘要翻译： 一种使用训练数据的统计模型对模拟电信号进行分类的系统，方法和计算机程序产品。 描述了一种技术来以使信号压缩最大化的方式对模拟电信号进行量化，同时最小化对压缩信号进行分类的能力的减小。 这些目标通过利用设计用于最小化对数似然比的功率损失的量化器来实现。 描述了另一种技术，以通过对经过所有维度可用的最大位数的量化特征向量的每个维度最佳地分配位数来增强量化过程。
-
公开(公告)号：US08271278B2
公开(公告)日：2012-09-18
申请号：US12753859
申请日：2010-04-03
CPC分类号： G10L17/06
摘要： A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.
摘要翻译： 一种使用训练数据的统计模型对模拟电信号进行分类的系统，方法和计算机程序产品。 描述了一种技术来以使信号压缩最大化的方式对模拟电信号进行量化，同时最小化对压缩信号进行分类的能力的减小。 这些目标通过利用设计用于最小化对数似然比的功率损失的量化器来实现。 描述了另一种技术，以通过对经过所有维度可用的最大位数的量化特征向量的每个维度最佳地分配位数来增强量化过程。
-
7.发明授权Methods and apparatus for secure and adaptive delivery of multimedia content 有权用于安全和自适应地传送多媒体内容的方法和装置公开(公告)号：US09071664B2
公开(公告)日：2015-06-30
申请号：US12533643
申请日：2009-07-31
CPC分类号： H04L65/602 , H04L29/06027 , H04L65/607
摘要： Techniques for securely and adaptively delivering multimedia content are disclosed in which a set of alternate access units for each time slot is obtained. Then, the encryption stream index of each access unit from the set of alternate access units of the previous time slot are obtained. An encryption stream index is then assigned to each access unit in the set of alternate access units in the current time slot, such that the encryption index increases over time. Thus, the invention overcomes the problem of encrypting a multimedia stream that may have multiple access units for each time slot by selecting the encryption index for each access unit such that the encryption index increases, regardless of which access unit the delivery system (e.g., server) selects for transmission.
摘要翻译： 公开了用于安全和自适应地递送多媒体内容的技术，其中获得了用于每个时隙的一组备用访问单元。 然后，获得来自前一时隙的一组备用访问单元的每个访问单元的加密流索引。 然后，将加密流索引分配给当前时隙中的备用访问单元集合中的每个访问单元，使得加密索引随时间增加。 因此，本发明克服了通过选择每个接入单元的加密索引来加密每个时隙可能具有多个接入单元的多媒体流的问题，使得加密索引增加，而不考虑哪个接入单元的传送系统（例如，服务器 ）选择进行传输。
-
公开(公告)号：US08855959B2
公开(公告)日：2014-10-07
申请号：US12871429
申请日：2010-08-30
IPC分类号： G01D3/00 , G01P21/00 , G01R31/319
CPC分类号： G01R31/31901 , G01R31/2894 , G01R31/3191
摘要： Processing test results from a plurality of individual semiconductor testers by analyzing each test result at an adaptive test engine. A centralized system jointly analyzes all the test results from the plurality of individual semiconductor testers. The adaptive test engine or the centralized system identifies, based on the analysis of each test result or the joint analysis of all the test results, one or more of: a test environmental issue, a tester variability issue, a tester calibration issue, a product variability issue, and a manufacturing process variability issue. The adaptive test engine or the centralized system determines whether one or more of the plurality of individual semiconductor testers causes one or more of the identified issues or whether semiconductor products tested by the plurality of individual semiconductor testers causes one or more of the identified issues.
-
公开(公告)号：US08666988B2
公开(公告)日：2014-03-04
申请号：US12466101
申请日：2009-05-14
CPC分类号： H04L51/12
摘要： According to an exemplary embodiment of the present invention, a method to configure a network of classifiers includes configuring a plurality of classifiers in a network of classifiers, such that the configuring associates a plurality of operating points with each output branch, associating a different quality profile with each output point for each output branch in the plurality of classifiers, and storing the configured network of classifiers and quality profile associations in the computer system to be used for classifying future input data according to the network configuration and quality profile association. Each classifier comprises executable code that classifies the data. Each of said classifiers has a plurality of the output branches that each output the data to another classifier. Each operating point comprises a probability of determining that a data item input to the classifier has a particular characteristic and a probability that said determination falsely detected the characteristic.
摘要翻译： 根据本发明的示例性实施例，一种配置分类器网络的方法包括在分类器网络中配置多个分类器，使得所述配置将多个操作点与每个输出分支相关联，将不同质量分布 将多个分类器中的每个输出分支的每个输出点用于计算机系统中的分类器和质量配置文件关联的配置网络，以便根据网络配置和质量配置文件关联对未来的输入数据进行分类。 每个分类器包括对数据进行分类的可执行代码。 每个所述分类器具有多个输出分支，每个输出分支将数据输出到另一个分类器。 每个操作点包括确定输入到分类器的数据项具有特定特性的概率，以及所述确定错误地检测到该特性的概率。
-
10.发明申请OPTIMAL TEST FLOW SCHEDULING WITHIN AUTOMATED TEST EQUIPMENT FOR MINIMIZED MEAN TIME TO DETECT FAILURE 审中-公开在自动测试设备中进行最佳测试流程调度，以最小化平均时间来检测故障公开(公告)号：US20110288808A1
公开(公告)日：2011-11-24
申请号：US12784142
申请日：2010-05-20
申请人： Wei Fan , Nagui Halim , Mark C. Johnson , Srinivasan Parthasarathy , Deepak S. Turaga , Olivier Verscheure
发明人： Wei Fan , Nagui Halim , Mark C. Johnson , Srinivasan Parthasarathy , Deepak S. Turaga , Olivier Verscheure
CPC分类号： G06F11/27 , G01R31/2894
摘要： The present invention describes a method and system for optimizing a test flow within each ATE (Automated Test Equipment) station. The test flow includes a plurality of test blocks. A test block includes a plurality of individual tests. A computing system schedule the test flow based one or more of: a test failure model, test block duration and a yield model. The failure model determines an order or sequence of the test blocks. There are at least two failure models: independent failure model and dependant failure model. The yield model describes whether a semiconductor chip is defective or not. Upon completing the scheduling, the ATE station conducts tests according to the scheduled test flow. The present invention can also be applied to software testing.
摘要翻译： 本发明描述了用于优化每个ATE（自动测试设备）站内的测试流程的方法和系统。 测试流程包括多个测试块。 测试块包括多个单独测试。 计算系统基于以下一个或多个来计划测试流程：测试失败模型，测试块持续时间和产量模型。 故障模型确定测试块的顺序或顺序。 至少有两种故障模型：独立故障模型和依赖故障模型。 产量模型描述了半导体芯片是否有缺陷。 完成调度后，ATE站根据预定的测试流程进行测试。 本发明也可以应用于软件测试。
-
-
-
-
-
-
-
-
-
搜索结果
59 条记录 (耗时 0.042 秒)
