公开(公告)号：US5839103A

公开(公告)日：1998-11-17

申请号：US479012

申请日：1995-06-07

申请人： Richard J. Mammone ,  Kevin Farrell ,  Manish Sharma ,  Devang Naik ,  Xiaoyu Zhang ,  Khaled Assaleh ,  Han-Seng Liou

发明人： Richard J. Mammone ,  Kevin Farrell ,  Manish Sharma ,  Devang Naik ,  Xiaoyu Zhang ,  Khaled Assaleh ,  Han-Seng Liou

IPC分类号： G10L15/10 ,  G10L15/02 ,  G10L15/08 ,  G10L15/20 ,  G10L17/00 ,  G10L21/02 ,  G10L5/00

CPC分类号： G10L17/10 ,  G10L17/20 ,  G10L17/04 ,  G10L17/14 ,  G10L17/18 ,  G10L25/03

摘要： The present invention relates to a pattern recognition system which uses data fusion to combine data from a plurality of extracted features and a plurality of classifiers. Speaker patterns can be accurately verified with the combination of discriminant based and distortion based classifiers. A novel approach using a training set of a "leave one out" data can be used for training the system with a reduced data set. Extracted features can be improved with a pole filtered method for reducing channel effects and an affine transformation for improving the correlation between training and testing data.

摘要翻译： 本发明涉及使用数据融合来组合来自多个提取的特征的数据和多个分类器的模式识别系统。 可以通过基于判别式和基于失真的分类器的组合来准确地验证扬声器模式。 使用训练集“离开一个”数据的新颖方法可用于使用减少的数据集训练系统。 提取的特征可以通过用于减少信道效应的极点滤波方法和用于改善训练和测试数据之间的相关性的仿射变换来改进。

公开(公告)号：US06539352B1

公开(公告)日：2003-03-25

申请号：US08976280

申请日：1997-11-21

申请人： Manish Sharma ,  Xiaoyu Zhang ,  Richard J. Mammone

发明人： Manish Sharma ,  Xiaoyu Zhang ,  Richard J. Mammone

IPC分类号： G10L1700

CPC分类号： G10L17/10 ,  G10L15/04 ,  G10L15/07 ,  G10L15/10 ,  G10L15/16 ,  G10L15/1815 ,  G10L17/04

摘要： The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word/key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

摘要翻译： 本发明的语音打印系统是一种基于词语的文本相关的自动说话人验证系统，其体现了用户可选择密码的能力，对词汇词或语言的选择没有限制。 自动盲语分割允许语音被分割成子词单元，而没有密码的任何语言知识。 使用多个分类器执行子字建模。 该系统还利用了诸如多分类器融合和数据重采样这样的概念来成功提高性能。 关键词/关键短语发现用于最佳地定位密码短语。 许多适应技术增加了基本系统的灵活性，包括：信道适应，融合适应，模型适应和阈值适配。

公开(公告)号：US06760701B2

公开(公告)日：2004-07-06

申请号：US10042832

申请日：2002-01-08

申请人： Manish Sharma ,  Xiaoyu Zhang ,  Richard J. Mammone

发明人： Manish Sharma ,  Xiaoyu Zhang ,  Richard J. Mammone

IPC分类号： G01L1700

CPC分类号： G10L17/10 ,  G10L15/04 ,  G10L15/07 ,  G10L15/10 ,  G10L15/16 ,  G10L15/1815 ,  G10L17/04

摘要： The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. An estimate of the enrollement channel and of the test channel is developed for inverse filtering of the enrollment or the test speech, respectively. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word/key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

摘要翻译： 本发明的语音打印系统是一种基于词语的文本相关的自动说话人验证系统，其体现了用户可选择密码的能力，对词汇词或语言的选择没有限制。 开发了入学通道和测试通道的估计，用于分别对入学或测试语音进行反向过滤。 自动盲语分割允许语音被分割成子词单元，而没有密码的任何语言知识。 使用多个分类器执行子字建模。 该系统还利用了诸如多分类器融合和数据重采样这样的概念来成功地提高性能。 关键词/关键短语发现用于最佳地定位密码短语。 许多适应技术增加了基本系统的灵活性，包括：信道适应，融合适应，模型适应和阈值适配。

公开(公告)号：US5862519A

公开(公告)日：1999-01-19

申请号：US827562

申请日：1997-04-01

申请人： Manish Sharma ,  Richard J. Mammone

发明人： Manish Sharma ,  Richard J. Mammone

IPC分类号： G10L11/00 ,  G10L15/04 ,  G10L5/06 ,  G10L9/00

CPC分类号： G10L25/48 ,  G10L15/04

摘要： The present invention relates to a method for segmenting speech into subword speech segments. Optimal boundary locations for each estimate of a number of segments are determined within an estimated range of the number of segments. In addition, an optimality criteria is found for each estimate of the number of segments within the range. Using the optimality criteria, the optimal number of subwords are determined. From the location of the boundaries and the optimal number of segments, data can be clustered or speech can be segmented. The method can be used in data processing systems, speaker verification, medium size vocabulary speech recognition systems, language identification systems and coarse subword level speech segmentation processes.

摘要翻译： 本发明涉及一种将语音分割为子词语音片段的方法。 在段的数量的估计范围内确定多个段的每个估计的最优边界位置。 此外，针对范围内的段数的每个估计找到最优性标准。 使用最优性标准，确定最佳子词数。 从边界的位置和段的最佳数量，可以对数据进行聚类或分割语音。 该方法可用于数据处理系统，扬声器验证，中等大小词汇语音识别系统，语言识别系统和粗略词级语音分割过程。

公开(公告)号：US06480825B1

公开(公告)日：2002-11-12

申请号：US09015393

申请日：1998-01-29

申请人： Manish Sharma ,  Richard J. Mammone

发明人： Manish Sharma ,  Richard J. Mammone

IPC分类号： G01L1700

CPC分类号： G10L17/26 ,  G07C9/00158 ,  G10L17/00 ,  G10L17/22

摘要： The present invention is a reliable system and method for detecting a recorded voice, which can be employed independently or to provide protection from fraudulent use of a recording to defeat an automatic speaker recognition system. Several techniques and systems are employed either independently or in combination to verify that a detected audio sample is live and not recorded. Temporal speech characteristics of an audio sample are analyzed to determine whether a sample under examination is so similar to a previous sample as to indicate a recording. Communications channel characteristics are examined to determine whether an sample was recorded on a different channel from a predetermined communications channel. A pattern classifier is trained to distinguish between live and recorded speech. Finally, an “audio watermark” is used to determine whether a detected audio sample is a recording of a previous communication by an authorized user. In addition, the various techniques of the present invention may be employed in serial or parallel combination with a variety of decisionmaking schemes to provide increased performance.

摘要翻译： 本发明是用于检测记录的声音的可靠系统和方法，其可以独立地使用或者提供防止欺骗性使用记录以防止自动说话人识别系统的保护。 独立地或组合地采用若干技术和系统来验证检测到的音频样本是否存在并且不被记录。 分析音频样本的时间语音特征，以确定正在检查的样本是否与之前的样本类似以指示记录。 检查通信信道特性以确定样本是否在与预定通信信道不同的信道上记录。 训练模式分类器来区分实况和录音。 最后，使用“音频水印”来确定检测到的音频样本是否是由授权用户进行的先前通信的记录。 此外，本发明的各种技术可以与各种决策方案串联或并行组合使用以提供增加的性能。

公开(公告)号：US10145707B2

公开(公告)日：2018-12-04

申请号：US13115940

申请日：2011-05-25

申请人： Mahesh Chowdhary ,  Manish Sharma ,  Arun Kumar ,  Anuraag Gupta ,  Prateek Agrawal

发明人： Mahesh Chowdhary ,  Manish Sharma ,  Arun Kumar ,  Anuraag Gupta ,  Prateek Agrawal

IPC分类号： G01C21/00 ,  G01C22/00 ,  A61B5/00 ,  A61B5/11 ,  G01C21/16 ,  G06F19/00 ,  G16H40/67

摘要： The present invention is related to detecting location of a navigation device using sensor data analysis, where the sensor is coupled to the navigation device. A hierarchical algorithm is used for making a series of decisions regarding the location of the navigation device, with each decision corresponding to a class among a plurality of classes related to the possible motion modes and/or precise location of the device, including the location of the device with respect to a person's body. By accurately identifying the device location, the hierarchical algorithm facilitates in providing relevant contextual information, thereby enhancing situational awareness.

公开(公告)号：US08824273B2

公开(公告)日：2014-09-02

申请号：US13027610

申请日：2011-02-15

申请人： Manish Sharma ,  Xinkuan Zhou ,  Joe Polland ,  Jun-Ming Wu

发明人： Manish Sharma ,  Xinkuan Zhou ,  Joe Polland ,  Jun-Ming Wu

IPC分类号： H04L1/00 ,  H04L29/14 ,  H04L12/56 ,  H04L12/28 ,  H04L12/26 ,  H04M11/06 ,  H04L12/24

CPC分类号： H04L69/40 ,  H04L12/2856 ,  H04L12/2898 ,  H04L41/0654 ,  H04L41/0681 ,  H04L41/0686 ,  H04L43/0811 ,  H04L45/28 ,  H04M11/062

摘要： A communication system that comprises at least two links to carry signals, a first communication unit and a second communication unit. The first communication unit comprises at least two ports, each port configured to transmit and receive signals; and a logic unit configured to process the signals transmitted and received by each of the at least two ports in the first communication unit. The second communication unit comprises at least two ports, each port configured to transmit and receive signals and coupled to a respective one of the at least two ports in the first communication unit via a respective one of the at least two links; a programmable logic unit configured to process the signals transmitted and received by each of the at least two ports in the second communication unit; and a processor. The processor is configured to detect a crossover connection between one of the at least two ports in the second communication unit and the respective one of the at least two ports in the first communication unit based on an analysis of a pair identifier field in a message received at the second communication unit, wherein the pair identifier field is separate from the address field of the received message.

摘要翻译： 一种包括至少两个用于承载信号的链路的通信系统，第一通信单元和第二通信单元。 第一通信单元包括至少两个端口，每个端口被配置为发送和接收信号; 以及逻辑单元，被配置为处理由所述第一通信单元中的所述至少两个端口中的每一个发送和接收的信号。 所述第二通信单元包括至少两个端口，每个端口被配置为经由所述至少两个链路中的相应一个发送和接收信号并且耦合到所述第一通信单元中的所述至少两个端口中的相应一个端口; 可编程逻辑单元，被配置为处理由所述第二通信单元中的所述至少两个端口中的每一个发送和接收的信号; 和处理器。 处理器被配置为基于对所接收的消息中的对标识符字段的分析来检测第二通信单元中的至少两个端口中的一个端口与第一通信单元中的至少两个端口中的相应一个之间的交叉连接 在第二通信单元处，其中对标识符字段与接收到的消息的地址字段分离。

公开(公告)号：US08792091B2

公开(公告)日：2014-07-29

申请号：US13584531

申请日：2012-08-13

申请人： Ian McClean ,  Manish Sharma

发明人： Ian McClean ,  Manish Sharma

IPC分类号： G01N21/00 ,  G01M11/00 ,  H04B10/071

CPC分类号： H04B10/071 ,  G01M11/3145 ,  G01M11/3154

摘要： Fiber-optic communications systems are provided for optical communications networks. Fiber-optic communications links may be provided that use spans of transmission fiber to carry optical data signals on wavelength-division-multiplexing channels at different wavelengths between nodes. An apparatus and method are disclosed to use one optical light source per node to perform OTDR and LCV to satisfy safety concerns and accelerate the verification of the integrity of optical fiber links, before the application of high Raman laser powered light sources to a fiber link. A system using only one receiver per node is also disclosed.

摘要翻译： 为光通信网络提供光纤通信系统。 可以提供光纤通信链路，其使用传输光纤的跨段在节点之间的不同波长的波分复用信道上携带光数据信号。 公开了一种装置和方法，在将高拉曼激光供电的光源应用于光纤链路之前，每个节点使用一个光学光源来执行OTDR和LCV以满足安全性问题并加速光纤链路完整性的验证。 还公开了每个节点仅使用一个接收机的系统。

公开(公告)号：US20130202297A1

公开(公告)日：2013-08-08

申请号：US13368254

申请日：2012-02-07

申请人： Massimo MARTINELLI ,  Manish Sharma ,  Ruipeng Sun ,  Mark H. Garrett ,  Aravanan Gurusami

发明人： Massimo MARTINELLI ,  Manish Sharma ,  Ruipeng Sun ,  Mark H. Garrett ,  Aravanan Gurusami

IPC分类号： H04J14/00

CPC分类号： G02B27/283 ,  G02B6/2817 ,  G02B6/3512 ,  G02B6/3518 ,  G02B6/3546 ,  G02B2006/1215

摘要： A multicast optical switch includes a free-space optical assembly of discrete splitters, cylindrical optics, and a linear array of reflective switching devices, such as microelectromechanical systems (MEMS) mirrors, to provide low-loss, high-performance multicast switching in a compact configuration. The assembly of optical splitters may include multiple planar lightwave circuit splitters or a multi-reflection beam splitter that includes a linear array of partially reflecting mirrors, each of a different reflectivity.

摘要翻译： 组播光学交换机包括离散分离器的自由空间光学组件，圆柱形光学器件和诸如微机电系统（MEMS）反射镜的反射式开关器件的线性阵列，以在紧凑的情况下提供低损耗，高性能的多播切换 组态。 光分路器的组件可以包括多个平面光波分路器或多反射分束器，其包括具有不同反射率的部分反射镜的线性阵列。

公开(公告)号：US20130021899A1

公开(公告)日：2013-01-24

申请号：US13187306

申请日：2011-07-20

申请人： Joe Polland ,  Clifton Powers ,  Manish Sharma ,  Laxman R. Anne ,  Yiu Lam Chan

发明人： Joe Polland ,  Clifton Powers ,  Manish Sharma ,  Laxman R. Anne ,  Yiu Lam Chan

IPC分类号： H04L12/26

CPC分类号： H04L12/2898 ,  H04M11/062

摘要： A communication comprises a plurality of digital subscriber line (DSL) links, a first node having at least one application port configured for an elastic service and a plurality of DSL ports, and a second node having at least one application port configured for an elastic service and a plurality of DSL ports. Each of the first and second nodes is configured to interleave data received over the at least one application port across the plurality of DSL ports, each DSL port allocated a set of DSL timeslots for transport of the data received over the at least one application port. When a failure is detected on one of the DSL links, each of the first and second nodes is configured to interleave the data received over the at least one application port across the remaining DSL ports not connected to the failed DSL link without adjusting the set of DSL timeslots allocated to each of the remaining DSL ports for transport of the data from the at least one application port.

摘要翻译： 通信包括多个数字用户线（DSL）链路，具有配置用于弹性服务的至少一个应用端口和多个DSL端口的第一节点以及具有被配置用于弹性服务的至少一个应用端口的第二节点 和多个DSL端口。 第一和第二节点中的每一个被配置为交织跨多个DSL端口上的至少一个应用端口接收的数据，每个DSL端口分配一组DSL时隙，用于传输在至少一个应用端口上接收的数据。 当在DSL链路之一上检测到故障时，第一和第二节点中的每一个被配置成交错在不连接到故障DSL链路的剩余DSL端口上的至少一个应用端口上接收的数据，而不调整该组 分配给每个剩余DSL端口的DSL时隙用于从至少一个应用端口传输数据。