专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09557178B2 Indoor positioning system 有权
标题翻译：室内定位系统
公开(公告)号：US09557178B2
公开(公告)日：2017-01-31
申请号：US14450890
申请日：2014-08-04
申请人： Tata Consultancy Services Ltd.
发明人： Avik Ghose , Arpan Pal , Anirban Dutta Choudhury , Vivek Chandel , Chirabrata Bhaumik , Tanushyam Chattopadhyay
IPC分类号： G01C21/20 , G01R33/038 , H04W4/04 , H04W64/00
CPC分类号： G01C21/206 , G01R33/038 , H04W4/04 , H04W64/00
摘要： An indoor positioning system and method of localizing a person/object in an indoor environment by identifying the orientation and direction of a person/object to provide a true location of the person/object without navigation errors. The system comprises magnets disposed on a doorway to create a unique magnetic field; a wireless communication unit comprising a magnetometer sensor to sense perturbations in each of the unique magnetic fields in the event that the person/object with the wireless communication unit passes through the doorway, and generate corresponding signals; a processor receiving the signals and extracting data from the same; and a backend server wirelessly communicating with the wireless communication unit, the backend server processing the data sample received from the wireless communication unit to identify the opening and the wireless communication unit to localize the person/object.
摘要翻译：一种室内定位系统和方法，其通过识别人/物体的方向和方向来定位人/物体在室内环境中，以提供人/物体的真实位置而不导航错误。该系统包括设置在门口上以产生唯一磁场的磁体; 一种无线通信单元，包括磁力计传感器，用于在与无线通信单元的人/物体通过门口的情况下感测每个独特磁场中的扰动，并产生相应的信号; 处理器接收信号并从其中提取数据; 以及与所述无线通信单元无线通信的后端服务器，所述后端服务器处理从所述无线通信单元接收到的所述数据样本，以识别所述开放部分，以及所述无线通信单元以使所述人/物体本地化。

2. 发明授权

US09552809B2 Document transcription system training 有权
标题翻译：文件转录系统培训
公开(公告)号：US09552809B2
公开(公告)日：2017-01-24
申请号：US15066677
申请日：2016-03-10
申请人： MModal IP LLC
发明人： Girija Yegnanarayanan , Michael Finke , Juergen Fritsch , Detlef Koll , Monika Woszczyna
IPC分类号： G10L15/06 , G10L15/193 , G10L15/26
CPC分类号： G10L15/063 , G10L15/193 , G10L15/26
摘要： A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.
摘要翻译：提供用于训练用于语音识别的声学模型的系统。特别地，这样的系统可以用于基于口语音频流和口头音频流的非文字转录来执行训练。这样的系统可以识别表示具有多个口头形式的概念的非文字记录中的文本。该系统可以尝试在音频流中识别在非文字转录中产生相应文本的音频流中的实际语音形式，从而产生更准确地表示语音音频流的经修改的脚本。修改和更准确的誊本可用于训练声学模型，从而产生比使用直接基于原始非文字誊本进行训练的常规技术产生的更好的声学模型。

3. 发明授权

US09502033B2 Distributed speech recognition using one way communication 有权
标题翻译：使用单向通信的分布式语音识别
公开(公告)号：US09502033B2
公开(公告)日：2016-11-22
申请号：US14627560
申请日：2015-02-20
申请人： MModal IP LLC
发明人： Eric Carraux , Detlef Koll
IPC分类号： G10L15/22 , G10L15/30 , G10L15/32
CPC分类号： G10L15/22 , G10L15/30 , G10L15/32
摘要： A speech recognition client sends a speech stream and control stream in parallel to a server-side speech recognizer over a network. The network may be an unreliable, low-latency network. The server-side speech recognizer recognizes the speech stream continuously. The speech recognition client receives recognition results from the server-side recognizer in response to requests from the client. The client may remotely reconfigure the state of the server-side recognizer during recognition.
摘要翻译：语音识别客户端通过网络将语音流和控制流并行发送到服务器端语音识别器。网络可能是不可靠的低延迟网络。服务器端语音识别器连续识别语音流。语音识别客户机根据来自客户端的请求从服务器端识别器接收识别结果。客户端可以在识别期间远程重新配置服务器端识别器的状态。

4. 发明授权

US09489375B2 Speech recognition using an operating system hooking component for context-aware recognition models 有权
标题翻译：语音识别使用操作系统挂钩组件进行上下文感知识别模型
公开(公告)号：US09489375B2
公开(公告)日：2016-11-08
申请号：US13526789
申请日：2012-06-19
申请人： Detlef Koll , Michael Finke
发明人： Detlef Koll , Michael Finke
IPC分类号： G06F17/20 , G10L21/00 , G06F17/27 , G10L15/183 , G06F9/44 , G10L15/26
CPC分类号： G10L15/063 , G06F3/04817 , G06F9/454 , G06F17/276 , G10L15/183 , G10L15/22 , G10L15/265 , G10L2015/0635 , G10L2015/223
摘要： Inputs provided into user interface elements of an application are observed. Records are made of the inputs and the state(s) the application was in while the inputs were provided. For each state, a corresponding language model is trained based on the input(s) provided to the application while the application was in that state. When the application is next observed to be in a previously-observed state, a language model associated with the application's current state is applied to recognize speech input provided by a user and thereby to generate speech recognition output that is provided to the application. An application's state at a particular time may include the user interface element(s) that are displayed and/or in focus at that time, and is determined by an operating system hooking component embedded in the automatic speech recognition system.
摘要翻译：观察到提供给应用程序的用户界面元素的输入。记录由输入和应用程序在提供输入时所处的状态组成。对于每个状态，在应用程序处于该状态时，基于提供给应用程序的输入来对相应的语言模型进行训练。当应用程序接下来观察到处于先前观察到的状态时，应用与应用程序的当前状态相关联的语言模型来识别由用户提供的语音输入，从而生成提供给应用的语音识别输出。在特定时间的应用程序的状态可以包括当时显示和/或聚焦的用户界面元素，并且由嵌入在自动语音识别系统中的操作系统挂钩组件确定。

5. 发明授权

US09454965B2 Content-based audio playback emphasis 有权
公开(公告)号：US09454965B2
公开(公告)日：2016-09-27
申请号：US14852021
申请日：2015-09-11
申请人： MModal IP LLC
发明人： Kjell Schubert , Juergen Fritsch , Michael Finke , Detlef Koll
IPC分类号： G10L15/00 , G10L15/26 , G10L15/22 , G10L21/04 , G06F17/27 , G10L15/18
CPC分类号： G10L15/26 , G06F17/273 , G06F17/2785 , G10L15/1807 , G10L15/22 , G10L15/265 , G10L21/04
摘要： Techniques are disclosed for facilitating the process of proofreading draft transcripts of spoken audio streams. In general, proofreading of a draft transcript is facilitated by playing back the corresponding spoken audio stream with an emphasis on those regions in the audio stream that are highly relevant or likely to have been transcribed incorrectly. Regions may be emphasized by, for example, playing them back more slowly than regions that are of low relevance and likely to have been transcribed correctly. Emphasizing those regions of the audio stream that are most important to transcribe correctly and those regions that are most likely to have been transcribed incorrectly increases the likelihood that the proofreader will accurately correct any errors in those regions, thereby improving the overall accuracy of the transcript.

6. 发明授权

US09342788B2 Polynomial method of constructing a non-deterministic (NP) turing machine 有权
标题翻译：构造非确定性（NP）图灵机的多项式方法
公开(公告)号：US09342788B2
公开(公告)日：2016-05-17
申请号：US14858427
申请日：2015-09-18
申请人： Sherwin Han
发明人： Sherwin Han
IPC分类号： G06N5/04 , G06N5/00 , G06N5/02
CPC分类号： G06N5/04 , G06N5/00 , G06N5/022
摘要： A nondeterministic Turing machine (NTM) performs computations using a spatial binary enumeration system, a three-dimensional relation system, a simulated-human logic system, and a bijective-set memory system. The NTM may be used to perform a variety of computational tasks, such as multiple sequence alignment, factorization, and other nondeterministic polynomial algorithms in polynomial time. The NTM may be constructed by a deterministic Turing machine (DTM) using the four systems listed above.
摘要翻译：非确定性图灵机（NTM）使用空间二进制枚举系统，三维关系系统，模拟人类逻辑系统和双射体存储系统执行计算。 NTM可以用于执行多项式时间中的各种计算任务，例如多序列比对，因式分解和其他非确定性多项式算法。 NTM可以由使用上述四种系统的确定性图灵机（DTM）构建。

7. 发明授权

US09286896B2 Document transcription system training 有权
公开(公告)号：US09286896B2
公开(公告)日：2016-03-15
申请号：US14280041
申请日：2014-05-16
申请人： MModal IP LLC
发明人： Girija Yegnanarayanan , Michael Finke , Juergen Fritsch , Detlef Koll , Monika Woszczyna
IPC分类号： G10L15/06 , G10L15/26 , G10L15/193
CPC分类号： G10L15/063 , G10L15/193 , G10L15/26
摘要： A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

8. 发明授权

US09250327B2 Method and apparatus for reducing satellite position message payload by adaptive data compression techniques 有权
标题翻译：用于通过自适应数据压缩技术减少卫星位置消息有效载荷的方法和装置
公开(公告)号：US09250327B2
公开(公告)日：2016-02-02
申请号：US13785514
申请日：2013-03-05
申请人： SubCarrier Systems Corporation
发明人： David Charles Kelley , Gregory John Berchin
IPC分类号： G01S19/07 , G01S19/41 , H03M7/30 , G01S19/00
CPC分类号： G01S19/07 , H03M7/30
摘要： An adaptive method by which Differential GNSS corrections may be compressed. Each measurement datum to be transmitted to a rover for satellite navigation purposes is decomposed into two parts, namely, an anchor value and a delta value, and in some instances an added third part termed a nonce value is used. Encoding parameters such as the number of bits assigned to each part of the measurement datum, the order of the models used to convey positional data, and scaling constants in the models, are adjusted adaptively based on changing data and/or transmission medium characteristics. Adaptive compression also allows for anomalous conditions such as out-of-range data values to be handled gracefully.
摘要翻译：可以压缩差分GNSS校正的自适应方法。要发送到用于卫星导航的漫游器的每个测量数据被分解成两部分，即锚值和增量值，并且在某些情况下，使用称为随机数值的附加的第三部分。基于改变的数据和/或传输介质特性，自适应地调整诸如分配给测量基准的每个部分的位数的编码参数，用于传送位置数据的模型的顺序和缩放常数。自适应压缩还允许正常处理异常条件，例如超范围数据值。

9. 发明授权

US09218156B2 Processing with compact arithmetic processing element 有权
标题翻译：使用紧凑的算术处理元件进行处理
公开(公告)号：US09218156B2
公开(公告)日：2015-12-22
申请号：US13849606
申请日：2013-03-25
申请人： Singular Computing LLC
发明人： Joseph Bates
IPC分类号： G06F7/38 , G06F7/483 , G06F7/523 , H03K19/177
CPC分类号： G06F7/483 , G06F7/38 , G06F7/4833 , G06F7/5235 , H03K19/17728
摘要： A processor or other device, such as a programmable and/or massively parallel processor or other device, includes processing elements designed to perform arithmetic operations (possibly but not necessarily including, for example, one or more of addition, multiplication, subtraction, and division) on numerical values of low precision but high dynamic range (“LPHDR arithmetic”). Such a processor or other device may, for example, be implemented on a single chip. Whether or not implemented on a single chip, the number of LPHDR arithmetic elements in the processor or other device in certain embodiments of the present invention significantly exceeds (e.g., by at least 20 more than three times) the number of arithmetic elements, if any, in the processor or other device which are designed to perform high dynamic range arithmetic of traditional precision (such as 32 bit or 64 bit floating point arithmetic).
摘要翻译：诸如可编程和/或大规模并行处理器或其他设备的处理器或其他设备包括被设计为执行算术运算（可能但不一定包括例如加法，乘法，减法和除法中的一个或多个）的处理元件）对低精度但高动态范围的数值（“LPHDR算术”）。这样的处理器或其他设备可以例如在单个芯片上实现。无论是否在单个芯片上实现，本发明的某些实施例中的处理器或其他设备中的LPHDR算术元件的数量显着地超过（例如，至少20倍以上）算术元素的数量（如果有的话），在处理器或其他设备中，被设计为执行传统精度的高动态范围算术（例如32位或64位浮点运算）。

10. 发明授权

US09141628B1 Relationship model for modeling relationships between equivalent objects accessible over a network 有权
标题翻译：用于建模通过网络访问的等效对象之间关系的关系模型
公开(公告)号：US09141628B1
公开(公告)日：2015-09-22
申请号：US12551732
申请日：2009-09-01
申请人： Gil Zimmermann , Ron Zalkind , Tsahy Shapsa
发明人： Gil Zimmermann , Ron Zalkind , Tsahy Shapsa
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30292 , G06F17/30106 , H04L67/10
摘要： A relationship model system automatically recognizes relationships among data in a local IT environment. Such data may be derived from multiple sources, such as multiple devices and/or software applications of different types. Such data are collected automatically, remotely, and transparently from the local IT environment. Relationships among the data are recognized automatically by correlating data from the multiple sources. Records of such relationships are stored remotely in a relationship model. The system may draw conclusions based on the recognized relationships and take actions in response to those conclusions.
摘要翻译：关系模型系统自动识别本地IT环境中的数据之间的关系。这样的数据可以来自多个源，例如不同类型的多个设备和/或软件应用。这些数据是从本地IT环境自动，远程和透明地收集的。通过将来自多个来源的数据相关联来自动识别数据之间的关系。这种关系的记录被远程存储在关系模型中。该制度可以根据公认的关系得出结论，并采取行动回应这些结论。

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