公开(公告)号：US20110307244A1

公开(公告)日：2011-12-15

申请号：US12814422

申请日：2010-06-11

申请人： Xiaodong He ,  Kristina Toutanova

发明人： Xiaodong He ,  Kristina Toutanova

IPC分类号： G06F17/28

CPC分类号： G06F17/2854 ,  G06F17/2818 ,  G06F17/2827

摘要： A joint optimization strategy is employed for combining translation hypotheses from multiple machine-translation systems. Decisions on word alignment, between the hypotheses, ordering, and selection of a combined translation output are made jointly in accordance with a set of features. Additional features that model alignment and ordering behavior are also provided and utilized.

摘要翻译： 联合优化策略用于组合来自多个机器翻译系统的翻译假设。 根据一组特征联合进行字对齐，组合翻译输出的假设，排序和选择之间的决定。 还提供和利用了模型对齐和排序行为的其他功能。

公开(公告)号：US07693713B2

公开(公告)日：2010-04-06

申请号：US11156106

申请日：2005-06-17

申请人： Xiaodong He ,  Jian Wu

发明人： Xiaodong He ,  Jian Wu

IPC分类号： G10L15/06

CPC分类号： G10L15/063

摘要： Speech models are trained using one or more of three different training systems. They include competitive training which reduces a distance between a recognized result and a true result, data boosting which divides and weights training data, and asymmetric training which trains different model components differently.

摘要翻译： 使用三种不同的训练系统中的一种或多种来训练语音模型。 它们包括减少识别结果与真实结果之间的距离的竞争性训练，对训练数据进行分组和加权的数据提升以及不同模型组成部分的不对称训练。

公开(公告)号：US20080091424A1

公开(公告)日：2008-04-17

申请号：US11581673

申请日：2006-10-16

申请人： Xiaodong He ,  Li Deng

发明人： Xiaodong He ,  Li Deng

IPC分类号： G10L15/00

CPC分类号： G10L15/063 ,  G10L15/144

摘要： Hidden Markov Model (HMM) parameters are updated using update equations based on growth transformation optimization of a minimum classification error objective function. Using the list of N-best competitor word sequences obtained by decoding the training data with the current-iteration HMM parameters, the current HMM parameters are updated iteratively. The updating procedure involves using weights for each competitor word sequence that can take any positive real value. The updating procedure is further extended to the case where a decoded lattice of competitors is used. In this case, updating the model parameters relies on determining the probability for a state at a time point based on the word that spans the time point instead of the entire word sequence. This word-bound span of time is shorter than the duration of the entire word sequence and thus reduces the computing time.

摘要翻译： 使用基于最小分类误差目标函数的生长变换优化的更新方程来更新隐马尔可夫模型（HMM）参数。 使用通过使用当前迭代HMM参数对训练数据进行解码而获得的N个最佳竞争者词序列表，迭代地更新当前HMM参数。 更新过程涉及使用可以获得任何正实值的每个竞争者词序列的权重。 更新过程进一步扩展到使用竞争者的解码格子的情况。 在这种情况下，更新模型参数依赖于基于跨越时间点而不是整个单词序列的单词来确定在时间点的状态的概率。 这个字边界的时间范围比整个单词序列的持续时间短，从而减少了计算时间。

公开(公告)号：US20080052075A1

公开(公告)日：2008-02-28

申请号：US11509980

申请日：2006-08-25

申请人： Xiaodong He ,  Alex Acero ,  Dong Yu ,  Li Deng

发明人： Xiaodong He ,  Alex Acero ,  Dong Yu ,  Li Deng

IPC分类号： G10L15/14

CPC分类号： G10L15/063 ,  G10L15/144

摘要： A method and apparatus for training an acoustic model are disclosed. A training corpus is accessed and converted into an initial acoustic model. Scores are calculated for a correct class and competitive classes, respectively, for each token given the acoustic model. From this score a misclassification measure is calculated and then a loss function is calculated from the misclassification measure. The loss function also includes a margin value that varies over each iteration in the training. Based on the calculated loss function the acoustic model is updated, where the loss function with the margin value is minimized. This process repeats until such time as an empirical convergence is met.

摘要翻译： 公开了一种用于训练声学模型的方法和装置。 训练语料库被访问并转换成初始声学模型。 对于给定声学模型的每个令牌，分数是针对正确的班级和竞赛班分别计算的。 从该分数计算错误分类度量，然后根据误分类度量计算损失函数。 损失函数还包括在训练中每次迭代变化的保证金值。 基于计算的损耗函数，声学模型被更新，其中具有边际值的损失函数被最小化。 该过程重复，直到满足经验收敛的时间为止。

公开(公告)号：US09292783B2

公开(公告)日：2016-03-22

申请号：US14342531

申请日：2012-03-20

申请人： Liangheng Xu ,  Kai Yang ,  Yun Gao ,  Jin Tao ,  Xiaodong He

发明人： Liangheng Xu ,  Kai Yang ,  Yun Gao ,  Jin Tao ,  Xiaodong He

IPC分类号： G06K19/06 ,  G06K19/077 ,  G06K19/073 ,  B29C65/48

CPC分类号： G06K19/07775 ,  B29C65/4835 ,  G06K19/0739 ,  G06K19/07786

摘要： The present invention provides a radio frequency identification electronic tag with diversion-proof function and a process for making the same. The radio frequency identification electronic tag with diversion-proof function is formed of a supporting layer, a release liner, an antenna and a chip, wherein the release liner is bonded to one side of the supporting layer to form an entity, the antenna is bonded to the other side of the release liner, or, the antenna is bonded to the two sides of the entity formed by the supporting layer and the release liner, and is connected via overbridge points on the antenna, the overbridge points run through the supporting layer and the release liner so that antennas at the two sides are switched into conduction; the chip is bonded to the antenna. Once the RFID tag with diversion-proof function is peeled off or transferred, its physical structure will be destroyed and the information contained therein cannot be read, achieving the object of incapable of being reused. At the same time, the thermosetting resins are bonded organically according to the processing technology of the RFID tag, then the bonding points and the overbridge points of the chip have higher bonding fastness with the supporting layer, it is not easy for the chip to peel off with the release liner and better overbridge effect is achieved, which can greatly improve the yield of the finished RFID tag with diversion-proof function.

摘要翻译： 本发明提供一种具有防分离功能的射频识别电子标签及其制造方法。 具有防转移功能的射频识别电子标签由支撑层，释放衬垫，天线和芯片形成，其中释放衬垫结合到支撑层的一侧以形成实体，天线被结合 或者天线结合到由支撑层和释放衬垫形成的实体的两侧，并且通过天线上的超桥点连接，跨桥点穿过支撑层 和释放衬垫，使得两侧的天线被切换成导通; 该芯片与天线结合。 一旦具有防转移功能的RFID标签被剥离或转移，其物理结构将被破坏，并且其中包含的信息不能被读取，从而达到无法再次使用的目的。 同时，根据RFID标签的加工工艺，热固性树脂有机结合，芯片的接合点和跨桥点与支撑层具有较高的粘接牢度，芯片不易剥离 脱离衬垫，实现更好的超桥效应，可以大大提高成品RFID标签的带防拆功能的产量。

公开(公告)号：US09201871B2

公开(公告)日：2015-12-01

申请号：US12814422

申请日：2010-06-11

申请人： Xiaodong He ,  Kristina Toutanova

发明人： Xiaodong He ,  Kristina Toutanova

IPC分类号： G06F17/20 ,  G06F17/28

CPC分类号： G06F17/2854 ,  G06F17/2818 ,  G06F17/2827

摘要： A joint optimization strategy is employed for combining translation hypotheses from multiple machine-translation systems. Decisions on word alignment, between the hypotheses, ordering, and selection of a combined translation output are made jointly in accordance with a set of features. Additional features that model alignment and ordering behavior are also provided and utilized.

摘要翻译： 联合优化策略用于组合来自多个机器翻译系统的翻译假设。 根据一组特征联合进行字对齐，组合翻译输出的假设，排序和选择之间的决定。 还提供和利用了模型对齐和排序行为的其他功能。

公开(公告)号：US20140326790A1

公开(公告)日：2014-11-06

申请号：US14342531

申请日：2012-03-20

申请人： Liangheng Xu ,  Kai Yang ,  Yun Gao ,  Jin Tao ,  Xiaodong He

发明人： Liangheng Xu ,  Kai Yang ,  Yun Gao ,  Jin Tao ,  Xiaodong He

IPC分类号： G06K19/077 ,  B29C65/48

CPC分类号： G06K19/07775 ,  B29C65/4835 ,  G06K19/0739 ,  G06K19/07786

摘要： The present invention provides a radio frequency identification electronic tag with diversion-proof function and a process for making the same. The radio frequency identification electronic tag with diversion-proof function is formed of a supporting layer, a release liner, an antenna and a chip, wherein the release liner is bonded to one side of the supporting layer to form an entity, the antenna is bonded to the other side of the release liner, or, the antenna is bonded to the two sides of the entity formed by the supporting layer and the release liner, and is connected via overbridge points on the antenna, the overbridge points run through the supporting layer and the release liner so that antennas at the two sides are switched into conduction; the chip is bonded to the antenna. Once the RFID tag with diversion-proof function is peeled off or transferred, its physical structure will be destroyed and the information contained therein cannot be read, achieving the object of incapable of being reused. At the same time, the thermosetting resins are bonded organically according to the processing technology of the RFID tag, then the bonding points and the overbridge points of the chip have higher bonding fastness with the supporting layer, it is not easy for the chip to peel off with the release liner and better overbridge effect is achieved, which can greatly improve the yield of the finished RFID tag with diversion-proof function.

摘要翻译： 本发明提供一种具有防分离功能的射频识别电子标签及其制造方法。 具有防转移功能的射频识别电子标签由支撑层，释放衬垫，天线和芯片形成，其中释放衬垫结合到支撑层的一侧以形成实体，天线被结合 或者天线结合到由支撑层和释放衬垫形成的实体的两侧，并且通过天线上的超桥点连接，跨桥点穿过支撑层 和释放衬垫，使得两侧的天线被切换成导通; 该芯片与天线结合。 一旦具有防转移功能的RFID标签被剥离或转移，其物理结构将被破坏，并且其中包含的信息不能被读取，从而达到无法再次使用的目的。 同时，根据RFID标签的加工工艺，热固性树脂有机结合，芯片的接合点和跨桥点与支撑层具有较高的粘接牢度，芯片不易剥离 脱离衬垫，实现更好的超桥效应，可以大大提高成品RFID标签的带防拆功能的产量。

公开(公告)号：US08185376B2

公开(公告)日：2012-05-22

申请号：US11384401

申请日：2006-03-20

申请人： Min Chu ,  Yi Ning Chen ,  Shiun-Zu Kuo ,  Xiaodong He ,  Megan Riley ,  Kevin E. Feige ,  Yifan Gong

发明人： Min Chu ,  Yi Ning Chen ,  Shiun-Zu Kuo ,  Xiaodong He ,  Megan Riley ,  Kevin E. Feige ,  Yifan Gong

IPC分类号： G06F17/20 ,  G06F17/27

CPC分类号： G06F17/275

摘要： The language of origin of a word is determined by analyzing non-uniform letter sequence portions of the word.

摘要翻译： 通过分析单词的不均匀字母序列部分来确定单词的起始语言。

公开(公告)号：US07873209B2

公开(公告)日：2011-01-18

申请号：US11700664

申请日：2007-01-31

申请人： Li Deng ,  Xiaodong He ,  Qiang Fu

发明人： Li Deng ,  Xiaodong He ,  Qiang Fu

IPC分类号： G06K9/00 ,  G10L15/00

CPC分类号： G06K9/6217 ,  G10L15/142

摘要： Pattern model parameters are updated using update equations based on competing patterns that are identical to a reference pattern except for one segment at a time that is replaced with a competing segment. This allows pattern recognition parameters to be tuned one segment at a time, rather than have to try to model distinguishing features of the correct pattern model as a whole, according to an illustrative embodiment. A reference pattern and competing patterns are divided into pattern segments. A set of training patterns are generated by replacing one of the pattern segments in the reference pattern with a corresponding competing pattern segment. For each of the training patterns, a pattern recognition model is applied to evaluate a relative degree of correspondence of the reference pattern with the pattern signal compared to a degree of correspondence of the training patterns with the pattern signal.

摘要翻译： 基于与参考模式相同的竞争模式的更新方程来更新模式模型参数，除了一次被竞争的段替换的一个段。 这允许模式识别参数一次调整一个段，而不是根据说明性实施例而不必为整体模拟正确模式模型的区分特征。 参考模式和竞争模式分为模式段。 通过将参考图案中的一个图案片段替换为相应的竞争图案片段来生成一组训练图案。 对于每个训练模式，应用模式识别模型来评估参考模式与模式信号的相对程度，与训练模式与模式信号的对应程度相比较。

公开(公告)号：US20080201139A1

公开(公告)日：2008-08-21

申请号：US11708440

申请日：2007-02-20

申请人： Dong Yu ,  Alejandro Acero ,  Li Deng ,  Xiaodong He

发明人： Dong Yu ,  Alejandro Acero ,  Li Deng ,  Xiaodong He

IPC分类号： G10L15/00

CPC分类号： G10L15/063 ,  G10L2015/0631

摘要： A method and apparatus for training an acoustic model are disclosed. A training corpus is accessed and converted into an initial acoustic model. Scores are calculated for a correct class and competitive classes, respectively, for each token given the initial acoustic model. Also, a sample-adaptive window bandwidth is calculated for each training token. From the calculated scores and the sample-adaptive window bandwidth values, loss values are calculated based on a loss function. The loss function, which may be derived from a Bayesian risk minimization viewpoint, can include a margin value that moves a decision boundary such that token-to-boundary distances for correct tokens that are near the decision boundary are maximized. The margin can either be a fixed margin or can vary monotonically as a function of algorithm iterations. The acoustic model is updated based on the calculated loss values. This process can be repeated until an empirical convergence is met.

摘要翻译： 公开了一种用于训练声学模型的方法和装置。 训练语料库被访问并转换成初始声学模型。 对于给定初始声学模型的每个令牌，分数计算分别为正确的类和竞争类。 此外，针对每个训练令牌计算样本自适应窗口带宽。 从计算出的分数和采样自适应窗口带宽值，根据损失函数计算损失值。 可以从贝叶斯风险最小化观点导出的损失函数可以包括移动判定边界的边距值，使得靠近判定边界的正确令牌的令牌到边界的距离最大化。 边距可以是固定边距，也可以作为算法迭代的函数单调变化。 基于计算的损失值更新声学模型。 可以重复该过程，直到满足经验收敛。