专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明申请

US20120243670A1 Automatically Updating Meeting Information 有权
标题翻译：自动更新会议信息
公开(公告)号：US20120243670A1
公开(公告)日：2012-09-27
申请号：US13069591
申请日：2011-03-23
申请人： Lior Horesh , Dimitri Kanevsky , David Nahamoo , Tara N. Sainath
发明人： Lior Horesh , Dimitri Kanevsky , David Nahamoo , Tara N. Sainath
IPC分类号： H04M11/00 , G06F17/27
CPC分类号： G06Q10/109 , H04L12/1895 , H04L51/02
摘要： Techniques for automatically providing updated meeting information are provided. The techniques include facilitating receipt of a message pertaining to a meeting, automatically interpreting the message to determine if the message requires that meeting information be changed, automatically updating the meeting information if a change is required from the message, and automatically sending a message to each meeting participant informing each participant of the updated meeting information.
摘要翻译：提供了自动提供更新的会议信息的技术。这些技术包括促进收到与会议有关的消息，自动解释消息以确定消息是否要求更改会议信息，如果需要从消息中改变会自动更新会议信息，并自动向每个消息发送消息会议参与者通知每个参与者更新的会议信息。

42. 发明授权

US09177215B2 Sparse representation for dynamic sensor networks 有权
标题翻译：动态传感器网络的稀疏表示
公开(公告)号：US09177215B2
公开(公告)日：2015-11-03
申请号：US13443289
申请日：2012-04-10
申请人： Wilfredo Ferre , Dimitri Kanevsky , Tara N. Sainath , Marc Yvon
发明人： Wilfredo Ferre , Dimitri Kanevsky , Tara N. Sainath , Marc Yvon
IPC分类号： G06F11/00 , G06K9/00 , G01N33/00 , G06K9/62
CPC分类号： G06K9/00979 , G01N33/0075 , G06K9/6249
摘要： A method, an apparatus and an article of manufacture for evaluating data from a network of sensors. The method includes analyzing data received from at least one sensor using exemplar-based sparse representation processing to create a sparse representation of the data, determining at least one discrete sparse characteristic of an event in the data received from the at least one sensor based on the sparse representation of the data, and evaluating the at least one discrete sparse characteristic of an event in the data to perform at least one task associated with the representation of the event in the data.
摘要翻译：一种用于评估来自传感器网络的数据的方法，装置和制品。该方法包括使用基于示例的稀疏表示处理来分析从至少一个传感器接收的数据以创建数据的稀疏表示，基于所述至少一个传感器确定从所述至少一个传感器接收的数据中的事件的至少一个离散稀疏特性数据的稀疏表示，以及评估数据中的事件的至少一个离散稀疏特征，以执行与数据中的事件的表示相关联的至少一个任务。

43. 发明授权

US08867707B2 Automatically updating meeting information 有权
标题翻译：自动更新会议信息
公开(公告)号：US08867707B2
公开(公告)日：2014-10-21
申请号：US13069591
申请日：2011-03-23
申请人： Lior Horesh , Dimitri Kanevsky , David Nahamoo , Tara N. Sainath
发明人： Lior Horesh , Dimitri Kanevsky , David Nahamoo , Tara N. Sainath
IPC分类号： H04M11/00 , H04L12/18 , H04L12/58 , G06Q10/10
CPC分类号： G06Q10/109 , H04L12/1895 , H04L51/02
摘要： Techniques for automatically providing updated meeting information are provided. The techniques include facilitating receipt of a message pertaining to a meeting, automatically interpreting the message to determine if the message requires that meeting information be changed, automatically updating the meeting information if a change is required from the message, and automatically sending a message to each meeting participant informing each participant of the updated meeting information.
摘要翻译：提供了自动提供更新的会议信息的技术。这些技术包括促进收到与会议有关的消息，自动解释消息以确定消息是否要求更改会议信息，如果需要从消息中改变会自动更新会议信息，并自动向每个消息发送消息会议参与者通知每个参与者更新的会议信息。

44. 发明授权

US08566270B2 Sparse representations for text classification 有权
标题翻译：文本分类的稀疏表示
公开(公告)号：US08566270B2
公开(公告)日：2013-10-22
申请号：US13242145
申请日：2011-09-23
申请人： Tara N. Sainath , Sameer R. Maskey , Bhuvana Ramabhadran , Dimitri Kanevsky
发明人： Tara N. Sainath , Sameer R. Maskey , Bhuvana Ramabhadran , Dimitri Kanevsky
IPC分类号： G06F17/00 , G06N5/02
CPC分类号： G06F17/2715 , G06F17/30707
摘要： A sparse representation method of text classification is described. An input text document is represented as a document feature vector y. A category dictionary H provides possible examples [h1; h2; . . . ; hn] of the document feature vector y. The input text document is classified using a sparse representation text classification algorithm that solves for y=Hβ where a sparseness condition is enforced on β to select a small number of examples from the dictionary H to describe the document feature vector y.
摘要翻译：描述了文本分类的稀疏表示方法。输入文本文档表示为文档特征向量y。类别字典H提供了可能的例子[h1; h2; 。。。 ; hn]的文档特征向量y。输入文本文档使用稀疏表示文本分类算法进行分类，该算法解决了y = Hbeta，其中在beta上执行稀疏条件以从字典H中选择少量示例来描述文档特征向量y。

45. 发明授权

US08527566B2 Directional optimization via EBW 有权
标题翻译：通过EBW定向优化
公开(公告)号：US08527566B2
公开(公告)日：2013-09-03
申请号：US12777768
申请日：2010-05-11
申请人： Dimitri Kanevsky , David Nahamoo , Bhuvana Ramabhadran , Tara N. Sainath
发明人： Dimitri Kanevsky , David Nahamoo , Bhuvana Ramabhadran , Tara N. Sainath
IPC分类号： G06F7/00
CPC分类号： G06F17/11
摘要： An optimization system and method includes determining a best gradient as a sparse direction in a function having a plurality of parameters. The sparse direction includes a direction that maximizes change of the function. This maximum change of the function is determined by performing an optimization process that gives maximum growth subject to a sparsity regularized constraint. An extended Baum Welch (EBW) method can be used to identify the sparse direction. A best step size is determined along the sparse direction by finding magnitudes of entries of direction that maximizes the function restricted to the sparse direction. A solution is recursively refined for the function optimization using a processor and storage media.
摘要翻译：优化系统和方法包括在具有多个参数的函数中确定最佳梯度作为稀疏方向。稀疏方向包括使功能变化最大化的方向。通过执行优化处理来确定功能的最大变化，该优化过程允许受到稀疏正则化约束的最大增长。扩展的Baum Welch（EBW）方法可用于识别稀疏方向。通过找到使限于稀疏方向的功能最大化的方向条目的大小，沿着稀疏方向确定最佳步长。使用处理器和存储介质递归地优化了功能优化的解决方案。

46. 发明申请

US20120078834A1 Sparse Representations for Text Classification 有权
标题翻译：文本分类的稀疏表示
公开(公告)号：US20120078834A1
公开(公告)日：2012-03-29
申请号：US13242145
申请日：2011-09-23
申请人： Tara N. Sainath , Sameer R. Maskey , Bhuvana Ramabhadran , Dimitri Kanevsky
发明人： Tara N. Sainath , Sameer R. Maskey , Bhuvana Ramabhadran , Dimitri Kanevsky
IPC分类号： G06N5/02
CPC分类号： G06F17/2715 , G06F17/30707
摘要： A sparse representation method of text classification is described. An input text document is represented as a document feature vector y. A category dictionary H provides possible examples [h1; h2; . . . ; hn] of the document feature vector y. The input text document is classified using a sparse representation text classification algorithm that solves for y=Hβ where a sparseness condition is enforced on β to select a small number of examples from the dictionary H to describe the document feature vector y.
摘要翻译：描述了文本分类的稀疏表示方法。输入文本文档表示为文档特征向量y。类别字典H提供了可能的例子[h1; h2; 。。。 ; hn]的文档特征向量y。输入文本文档使用解决y = H＆bgr的稀疏表示文本分类算法进行分类; 在“bgr”上执行稀疏条件从字典H中选择少量示例来描述文档特征向量y。

47. 发明申请

US20120078621A1 SPARSE REPRESENTATION FEATURES FOR SPEECH RECOGNITION 有权
标题翻译：用于语音识别的小数代表特征
公开(公告)号：US20120078621A1
公开(公告)日：2012-03-29
申请号：US12889845
申请日：2010-09-24
申请人： Dimitri Kanevsky , David Nahamoo , Bhuvana Ramabhadran , Tara N. Sainath
发明人： Dimitri Kanevsky , David Nahamoo , Bhuvana Ramabhadran , Tara N. Sainath
IPC分类号： G10L15/00
CPC分类号： G10L15/02
摘要： Techniques are disclosed for generating and using sparse representation features to improve speech recognition performance. In particular, principles of the invention provide sparse representation exemplar-based recognition techniques. For example, a method comprises the following steps. A test vector and a training data set associated with a speech recognition system are obtained. A subset of the training data set is selected. The test vector is mapped with the selected subset of the training data set as a linear combination that is weighted by a sparseness constraint such that a new test feature set is formed wherein the training data set is moved more closely to the test vector subject to the sparseness constraint. An acoustic model is trained on the new test feature set.The acoustic model trained on the new test feature set may be used to decode user speech input to the speech recognition system.
摘要翻译：公开了用于生成和使用稀疏表示特征以改善语音识别性能的技术。特别地，本发明的原理提供了基于示例的稀疏表示识别技术。例如，一种方法包括以下步骤。获得与语音识别系统相关联的测试向量和训练数据集。选择训练数据集的子集。将测试向量与所选择的训练数据集的子集映射为由稀疏约束加权的线性组合，使得形成新的测试特征集合，其中训练数据集更接近地移动到受测对象的测试向量稀疏约束在新的测试功能集上训练声学模型。在新测试特征集上训练的声学模型可以用于解码输入到语音识别系统的用户语音。

48. 发明申请

US20120053980A1 MANAGING ENCOUNTERS WITH PERSONS 有权
标题翻译：管理人员与人
公开(公告)号：US20120053980A1
公开(公告)日：2012-03-01
申请号：US12872042
申请日：2010-08-31
申请人： Sarah H. Basson , Dimitri Kanevsky , Clifford Alan Pickover , Tara N. Sainath
发明人： Sarah H. Basson , Dimitri Kanevsky , Clifford Alan Pickover , Tara N. Sainath
IPC分类号： G06Q10/00
CPC分类号： G06Q10/06316
摘要： Techniques are disclosed for facilitating coordination of user activities in accordance with information processing systems and, more particularly, to techniques for managing encounters with persons using such information processing systems. For example, a method for facilitating user coordination of one or more activities comprises the following steps. User personal preference input for managing an encounter with at least one other person is accepted. Input of at least one user schedule entry is received. Schedule entries of the at least one other person are evaluated and it is automatically determined whether there is an overlap between the at least one user schedule entry and the schedule entries of the at least one other person. A response to a determined overlap is automatically determined. The user personal preference input may comprise an indication of whether the user wishes to avoid an encounter with the at least one other person or coordinate an encounter with the at least one other person.
摘要翻译：公开了用于促进根据信息处理系统的用户活动的协调的技术，更具体地，涉及用于管理与使用这种信息处理系统的人的遭遇的技术。例如，用于促进一个或多个活动的用户协调的方法包括以下步骤。用于管理与至少一个其他人的遭遇的用户个人偏好输入被接受。接收至少一个用户日程表条目的输入。对至少一个其他人的计划条目进行评估，并且自动确定该至少一个用户日程表条目和该至少一个其他人的日程表条目之间是否存在重叠。自动确定对确定的重叠的响应。用户个人偏好输入可以包括用户是否希望避免与至少一个其他人的遭遇或协调与至少一个其他人的遭遇的指示。

49. 发明申请

US20090259471A1 DISTANCE METRICS FOR UNIVERSAL PATTERN PROCESSING TASKS 有权
标题翻译：用于通用图案处理任务的距离度量
公开(公告)号：US20090259471A1
公开(公告)日：2009-10-15
申请号：US12101791
申请日：2008-04-11
申请人： Dimitri KANEVSKY , David Nahamoo , Tara N. Sainath
发明人： Dimitri KANEVSKY , David Nahamoo , Tara N. Sainath
IPC分类号： G10L13/08
CPC分类号： G10L17/04 , G10L15/063
摘要： A universal pattern processing system receives input data and produces output patterns that are best associated with said data. The system uses input means receiving and processing input data, a universal pattern decoder means transforming models using the input data and associating output patterns with original models that are changed least during transforming, and output means outputting best associated patterns chosen by a pattern decoder means.
摘要翻译：通用模式处理系统接收输入数据并产生最好与所述数据相关联的输出模式。该系统使用输入装置接收和处理输入数据，通用模式解码器装置使用输入数据变换模型，并将输出模式与在变换期间最小变化的原始模型相关联，以及输出装置输出由模式解码器装置选择的最佳相关模式。

50. 发明申请

US20120253784A1 LANGUAGE TRANSLATION BASED ON NEARBY DEVICES 审中-公开
标题翻译：基于近邻设备的语言翻译
公开(公告)号：US20120253784A1
公开(公告)日：2012-10-04
申请号：US13077110
申请日：2011-03-31
申请人： Sameer Maskey , Dimitri Kanevasky , Tara N. Sainath , Bhuvana Ramabhadran
发明人： Sameer Maskey , Dimitri Kanevasky , Tara N. Sainath , Bhuvana Ramabhadran
IPC分类号： G06F17/28
CPC分类号： G06F17/289
摘要： A device, method, and computer program for performing language translation. An example embodiment may include a communications module configured to receive device data from a nearby device. A constraint module is configured to limit a translation domain of the language translation based on the device data. Language translation is performed within the limited translation domain.
摘要翻译：用于执行语言翻译的设备，方法和计算机程序。示例实施例可以包括被配置为从附近设备接收设备数据的通信模块。约束模块被配置为基于设备数据来限制语言翻译的翻译域。语言翻译在有限的翻译域内进行。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式