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. 发明申请

US20140001158A1 SYSTEMS AND METHODS FOR REPAIRING ENCASED COMPONENTS 审中-公开
标题翻译：修复组件的系统和方法
公开(公告)号：US20140001158A1
公开(公告)日：2014-01-02
申请号：US13534062
申请日：2012-06-27
申请人： Zhipeng Zhang , Andrew Lee Trimmer , Mark James Cintula , Prabhjot Singh , Arvind Rangarajan
发明人： Zhipeng Zhang , Andrew Lee Trimmer , Mark James Cintula , Prabhjot Singh , Arvind Rangarajan
IPC分类号： B23H1/04
CPC分类号： B23H1/04 , B23H9/10
摘要： A system for repairing a component is provided. The system includes an electrochemical machining unit and a tool delivery apparatus. The electrochemical machining unit includes an electrode, a power supply configured to energize the electrode and the component, and a machining solution source configured to pass a machining solution between the component and the electrode. The tool delivery apparatus includes a number of linkage elements pivotally connected and configured to carry the electrode. The tool delivery apparatus further includes an actuation element configured to actuate the linkage elements to move the electrode. A tool delivery apparatus and a method for repairing a component disposed within a case are also presented.
摘要翻译：提供了一种用于修复组件的系统。该系统包括电化学加工单元和工具输送装置。电化学加工单元包括电极，被配置为使电极和部件通电的电源，以及被配置为在部件和电极之间通过加工溶液的加工液源。工具传送装置包括枢转地连接和配置为承载电极的多个连接元件。工具传送装置还包括致动元件，其构造成致动联动元件以移动电极。还提出了一种用于修理设置在壳体内的部件的工具传送装置和方法。

2. 发明授权

US08713775B2 Apparatus and method for servicing dynamoelectric machine components in-situ 失效
标题翻译：现场维修电机组件的设备及方法
公开(公告)号：US08713775B2
公开(公告)日：2014-05-06
申请号：US13161579
申请日：2011-06-16
申请人： Zhipeng Zhang , Philip Alexander Shoemaker , Robert Jeffrey Pieciuk , Weston Blaine Griffin , Arvind Rangarajan , Diego Quinones , Prabhjot Singh
发明人： Zhipeng Zhang , Philip Alexander Shoemaker , Robert Jeffrey Pieciuk , Weston Blaine Griffin , Arvind Rangarajan , Diego Quinones , Prabhjot Singh
IPC分类号： B25B27/14 , B23P6/00
CPC分类号： F01D5/005 , B23P6/02 , F01D25/285 , F05D2230/80
摘要： An apparatus and method are provided for servicing a dynamoelectric machine component. The apparatus includes a tool delivery mechanism adapted for delivering a tool to a desired location in the dynamoelectric machine, and a tool support fixture adapted to be secured onto the body of the dynamoelectric machine, where the tool support fixture can be used for supporting and adjusting the tool delivery mechanism. A sleeve mechanism is attached to the tool support fixture, and the sleeve mechanism is disposed around a portion of the tool delivery mechanism. The apparatus is adapted to service the component of the dynamoelectric machine in-situ.
摘要翻译：提供了一种用于维修电动机器部件的装置和方法。该装置包括适于将工具传送到电动机中的期望位置的工具传送机构，以及适于固定在电动机的主体上的工具支撑夹具，其中工具支撑夹具可用于支撑和调节工具传递机制。套筒机构附接到工具支撑固定件，并且套筒机构设置在工具传送机构的一部分周围。该装置适用于现场维修电动机组件。

3. 发明申请

US20120317771A1 APPARATUS AND METHOD FOR SERVICING DYNAMOELECTRIC MACHINE COMPONENTS IN-SITU 失效
标题翻译：用于维修动态电机组件的装置和方法
公开(公告)号：US20120317771A1
公开(公告)日：2012-12-20
申请号：US13161579
申请日：2011-06-16
申请人： Zhipeng Zhang , Philip Alexander Shoemaker , Robert Jeffrey Pieciuk , Weston Blaine Griffin , Arvind Rangarajan , Diego Quinones , Prabhjot Singh
发明人： Zhipeng Zhang , Philip Alexander Shoemaker , Robert Jeffrey Pieciuk , Weston Blaine Griffin , Arvind Rangarajan , Diego Quinones , Prabhjot Singh
IPC分类号： B23P6/00 , B23P23/00
CPC分类号： F01D5/005 , B23P6/02 , F01D25/285 , F05D2230/80
摘要： An apparatus and method are provided for servicing a dynamoelectric machine component. The apparatus includes a tool delivery mechanism adapted for delivering a tool to a desired location in the dynamoelectric machine, and a tool support fixture adapted to be secured onto the body of the dynamoelectric machine, where the tool support fixture can be used for supporting and adjusting the tool delivery mechanism. A sleeve mechanism is attached to the tool support fixture, and the sleeve mechanism is disposed around a portion of the tool delivery mechanism. The apparatus is adapted to service the component of the dynamoelectric machine in-situ.
摘要翻译：提供了一种用于维修电动机器部件的装置和方法。该装置包括适于将工具传送到电动机中的期望位置的工具传送机构，以及适于固定在电动机的主体上的工具支撑夹具，其中工具支撑夹具可用于支撑和调节工具传递机制。套筒机构附接到工具支撑固定件，并且套筒机构设置在工具传送机构的一部分周围。该装置适用于现场维修电动机组件。

4. 发明申请

US20050080623A1 Noise adaptation system of speech model, noise adaptation method, and noise adaptation program for speech recognition 有权
标题翻译：语音模型噪声适应系统，噪声适应方法和语音识别噪声适应程序
公开(公告)号：US20050080623A1
公开(公告)日：2005-04-14
申请号：US10920461
申请日：2004-08-18
申请人： Sadaoki Furui , Zhipeng Zhang , Tsutomu Horikoshi , Toshiaki Sugimura
发明人： Sadaoki Furui , Zhipeng Zhang , Tsutomu Horikoshi , Toshiaki Sugimura
IPC分类号： G10L15/02 , G10L15/06 , G10L15/14 , G10L15/20 , G10L15/00
CPC分类号： G10L15/065 , G10L21/0216
摘要： An object of the present invention is to facilitate dealing with noisy speech with varying SNR and save calculation costs by generating a speech model with a single-tree-structure and using the model for speech recognition. Every piece of noise data stored in a noise database is used under every SNR condition to calculate the distance between all noise models with the SNR conditions and the noise-added speech is clustered. Based on the result of the clustering, a single-tree-structure model space into which the noise and SNR are integrated is generated (steps S1 to S5). At a noise extraction step (step S6), inputted noisy speech to be recognized is analyzed to extract a feature parameter string and the likelihoods of HMMs are compared one another to select an optimum model from the tree-structure noisy speech model space (step S7). Linear transformation is applied to the selected noisy speech model space so that the likelihood is maximized (step S8).
摘要翻译：本发明的一个目的是便于处理具有变化的SNR的噪声语音，并且通过用单树结构生成语音模型并使用语音识别模型来节省计算成本。在每个SNR条件下使用存储在噪声数据库中的每条噪声数据，以计算所有噪声模型与SNR条件之间的距离，并且将噪声添加语音聚类。基于聚类的结果，生成其中积分噪声和SNR的单树结构模型空间（步骤S1至S5）。在噪声提取步骤（步骤S6）中，分析输入的要识别的噪声语音以提取特征参数串，并将HMM的可能性彼此进行比较，以从树结构噪声语音模型空间中选择最佳模型（步骤S7 ）。将线性变换应用于所选择的噪声语音模型空间，使得似然性最大化（步骤S8）。

5. 发明授权

US09869161B2 Gas vent system and methods of operating the same 有权
公开(公告)号：US09869161B2
公开(公告)日：2018-01-16
申请号：US14570698
申请日：2014-12-15
申请人： Jeremy Daniel VanDam , Zhipeng Zhang , Ameen Aboel Hassan Muhammed
发明人： Jeremy Daniel VanDam , Zhipeng Zhang , Ameen Aboel Hassan Muhammed
IPC分类号： E21B43/08 , E21B43/38 , E21B34/06 , E21B43/12 , E21B43/30
CPC分类号： E21B34/066 , E21B43/12 , E21B43/305 , E21B43/38
摘要： A gas intake apparatus for use in a wellbore configured to channel a mixture of fluids and solids includes a housing defining a chamber and at least one gas intake passage in flow communication with the chamber. The gas intake apparatus further includes a gas intake mechanism coupled to the housing at the at least one gas intake passage. The gas intake mechanism is configured to facilitate a flow of gaseous substances therethrough and to restrict a flow of solids and liquids therethrough.

6. 发明授权

US07424426B2 Noise adaptation system of speech model, noise adaptation method, and noise adaptation program for speech recognition 有权
标题翻译：语音模型噪声适应系统，噪声适应方法和语音识别噪声适应程序
公开(公告)号：US07424426B2
公开(公告)日：2008-09-09
申请号：US10920461
申请日：2004-08-18
申请人： Sadaoki Furui , Zhipeng Zhang , Tsutomu Horikoshi , Toshiaki Sugimura
发明人： Sadaoki Furui , Zhipeng Zhang , Tsutomu Horikoshi , Toshiaki Sugimura
IPC分类号： G10L15/00
CPC分类号： G10L15/065 , G10L21/0216
摘要： An object of the present invention is to facilitate dealing with noisy speech with varying SNR and save calculation costs by generating a speech model with a single-tree-structure and using the model for speech recognition.Every piece of noise data stored in a noise database is used under every SNR condition to calculate the distance between all noise models with the SNR conditions and the noise-added speech is clustered. Based on the result of the clustering, a single-tree-structure model space into which the noise and SNR are integrated is generated (steps S1 to S5). At a noise extraction step (step S6), inputted noisy speech to be recognized is analyzed to extract a feature parameter string and the likelihoods of HMMs are compared one another to select an optimum model from the tree-structure noisy speech model space (step S7). Linear transformation is applied to the selected noisy speech model space so that the likelihood is maximized (step S8).
摘要翻译：本发明的一个目的是便于处理具有变化的SNR的噪声语音，并且通过用单树结构生成语音模型并使用语音识别模型来节省计算成本。在每个SNR条件下使用存储在噪声数据库中的每条噪声数据，以计算所有噪声模型与SNR条件之间的距离，并且将噪声添加语音聚类。基于聚类的结果，生成其中积分噪声和SNR的单树结构模型空间（步骤S1至S5）。在噪声提取步骤（步骤S6），分析输入的要识别的噪声语音以提取特征参数串，并将HMM的可能性彼此进行比较，以从树结构噪声语音模型空间中选择最佳模型（步骤 S 7）。将线性变换应用于所选择的噪声语音模型空间，使得似然性最大化（步骤S 8）。

7. 发明授权

US08238525B2 Voice recognition server, telephone equipment, voice recognition system, and voice recognition method 失效
标题翻译：语音识别服务器，电话设备，语音识别系统和语音识别方法
公开(公告)号：US08238525B2
公开(公告)日：2012-08-07
申请号：US12693796
申请日：2010-01-26
申请人： Zhipeng Zhang , Hirotaka Furukawa
发明人： Zhipeng Zhang , Hirotaka Furukawa
IPC分类号： H04M1/64 , G10L15/26
CPC分类号： H04M3/42153 , G10L15/183 , G10L15/30 , G10L2015/228 , H04M2201/40 , H04M2201/405 , H04M2250/66
摘要： A voice recognition server 200 has a voice reception unit 202 which receives a voice from a telephone equipment 100, a model storage unit 208 which stores at least one acoustic model and at least one language model used for converting the voice received by the voice reception unit 202, to character data, a number decision unit 204 which decides a current calling number and a second number of the telephone equipment 100, a model selection unit 206 which selects an acoustic model stored in the model storage unit 208, based on the current calling number and the second number, and which selects a language model stored in the model storage unit 208, based on the current calling number, and a voice recognition unit 210 which converts the voice received by the voice reception unit 202, to character data, based on the acoustic model and the language model selected by the model selection unit 206.
摘要翻译：语音识别服务器200具有从电话设备100接收语音的语音接收单元202，存储至少一个声学模型的模型存储单元208和用于转换由语音接收单元接收的语音的至少一种语言模型 202，对于字符数据，确定当前主叫号码的号码决定单元204和电话设备100的第二号码，选择存储在模型存储单元208中的声学模型的模型选择单元206，基于当前呼叫基于当前主叫号码选择存储在模型存储单元208中的语言模型和将由语音接收单元202接收的语音转换为基于字符数据的语音识别单元210 在由模型选择单元206选择的声学模型和语言模型上。

8. 发明申请

US20160084042A1 GAS VENT SYSTEM AND METHODS OF OPERATING THE SAME 有权
标题翻译：气体通风系统及其运行方法
公开(公告)号：US20160084042A1
公开(公告)日：2016-03-24
申请号：US14570698
申请日：2014-12-15
申请人： Jeremy Daniel VanDam , Zhipeng Zhang , Ameen Aboel Hassan Muhammed
发明人： Jeremy Daniel VanDam , Zhipeng Zhang , Ameen Aboel Hassan Muhammed
IPC分类号： E21B41/00 , E21B44/00 , E21B47/00 , E21B43/08 , E21B33/12
CPC分类号： E21B34/066 , E21B43/12 , E21B43/305 , E21B43/38
摘要： A gas intake apparatus for use in a wellbore configured to channel a mixture of fluids and solids includes a housing defining a chamber and at least one gas intake passage in flow communication with the chamber. The gas intake apparatus further includes a gas intake mechanism coupled to the housing at the at least one gas intake passage. The gas intake mechanism is configured to facilitate a flow of gaseous substances therethrough and to restrict a flow of solids and liquids therethrough.
摘要翻译：一种用于在井眼中配置以引导流体和固体的混合物的气体的进气装置包括限定腔室的壳体和与腔室流动连通的至少一个气体进入通道。进气装置还包括在至少一个进气通道处联接到壳体的进气机构。气体吸入机构构造成促进气体物质流过其中并限制固体和液体通过其中的流动。

9. 发明授权

US07552049B2 Noise adaptation system of speech model, noise adaptation method, and noise adaptation program for speech recognition 失效
标题翻译：语音模型噪声适应系统，噪声适应方法和语音识别噪声适应程序
公开(公告)号：US07552049B2
公开(公告)日：2009-06-23
申请号：US10796283
申请日：2004-03-10
申请人： Zhipeng Zhang , Kiyotaka Otsuji , Toshiaki Sugimura , Sadaoki Furui
发明人： Zhipeng Zhang , Kiyotaka Otsuji , Toshiaki Sugimura , Sadaoki Furui
IPC分类号： G10L15/00
CPC分类号： G10L15/20
摘要： An object of the present invention is to enable optimal clustering for many types of noise data and to improve the accuracy of estimation of a speech model sequence of input speech. Noise is added to speech in accordance with noise-to-signal ratio conditions to generate noise-added speech (step S1), the mean value of speech cepstral is subtracted from the generated, noise-added speech (step 2), a Gaussian distribution model of each piece of noise-added speech is created (step S3), the likelihoods of the pieces of noise-added speech are calculated to generate a likelihood matrix (step S4) to obtain a clustering result. An optimum model is selected (step S7) and linear transformation is performed to provide a maximized likelihood (step S8). Because noise-added speech is consistently used both in clustering and model learning, clustering for many types of noise data and an accurate estimation of a speech model sequence can be achieved.
摘要翻译：本发明的一个目的是为多种类型的噪声数据实现最佳聚类，并提高输入语音的语音模型序列的估计精度。根据噪声信号比率条件将噪声添加到语音中以产生噪声添加语音（步骤S1），从产生的噪声添加语音（步骤2）中减去语音倒频谱的平均值，高斯分布创建每个噪声添加语音的模型（步骤S3），计算噪声添加语音片段的可能性，以生成似然矩阵（步骤S4）以获得聚类结果。选择最佳模型（步骤S7），并执行线性变换以提供最大似然（步骤S8）。因为在聚类和模型学习中始终使用增加噪音的语音，所以可以实现许多类型的噪声数据的聚类和语音模型序列的精确估计。

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