公开(公告)号：US09799333B2

公开(公告)日：2017-10-24

申请号：US14840089

申请日：2015-08-31

申请人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

发明人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC分类号： G10L15/00 ,  G10L15/22 ,  G10L15/14 ,  G10L15/08

CPC分类号： G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

摘要： A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

公开(公告)号：US09177547B2

公开(公告)日：2015-11-03

申请号：US13926659

申请日：2013-06-25

申请人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

发明人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC分类号： G10L15/22 ,  G10L15/14 ,  G10L15/08

CPC分类号： G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

摘要： A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

摘要翻译： 提供了一种执行语音处理的系统和方法。 系统包括被配置为接收包括语音的信号的音频检测系统和其中存储有存储有数据库中与每个关键字相关联的过滤器的集合的关键字模型的数据库的存储器。 处理器被配置为从音频检测系统接收包括语音的信号，将包括语音的信号分解为稀疏语音脉冲集合，并访问关键字数据库，并将稀疏语音脉冲集合与滤波器组合进行卷积。 处理器还被配置为基于基于识别的关键词的卷积和控制操作电子系统的结果来识别包括语音的信号内的关键字。

公开(公告)号：US20150371635A1

公开(公告)日：2015-12-24

申请号：US14840089

申请日：2015-08-31

申请人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

发明人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC分类号： G10L15/22

CPC分类号： G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

摘要： A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

摘要翻译： 提供了一种执行语音处理的系统和方法。 系统包括被配置为接收包括语音的信号的音频检测系统和其中存储有存储有数据库中与每个关键字相关联的过滤器的集合的关键字模型的数据库的存储器。 处理器被配置为从音频检测系统接收包括语音的信号，将包括语音的信号分解为稀疏语音脉冲集合，并访问关键字数据库，并将稀疏语音脉冲集合与滤波器组合进行卷积。 处理器还被配置为基于基于识别的关键词的卷积和控制操作电子系统的结果来识别包括语音的信号内的关键字。

公开(公告)号：US20140379347A1

公开(公告)日：2014-12-25

申请号：US13926659

申请日：2013-06-25

申请人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

发明人： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC分类号： G10L15/02 ,  G10L15/187

CPC分类号： G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

摘要： A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

摘要翻译： 提供了一种执行语音处理的系统和方法。 系统包括被配置为接收包括语音的信号的音频检测系统和其中存储有存储有数据库中与每个关键字相关联的过滤器的集合的关键字模型的数据库的存储器。 处理器被配置为从音频检测系统接收包括语音的信号，将包括语音的信号分解为稀疏语音脉冲集合，并访问关键字数据库，并将稀疏语音脉冲集合与滤波器组合进行卷积。 处理器还被配置为基于基于识别的关键词的卷积和控制操作电子系统的结果来识别包括语音的信号内的关键字。

公开(公告)号：US07595874B1

公开(公告)日：2009-09-29

申请号：US11672794

申请日：2007-02-08

申请人： Vladimir M. Pelekhaty ,  Anatoliy Kachurin ,  William Warren ,  Kenneth Church ,  Heather Fahlenkamp ,  Russell Higbee

发明人： Vladimir M. Pelekhaty ,  Anatoliy Kachurin ,  William Warren ,  Kenneth Church ,  Heather Fahlenkamp ,  Russell Higbee

IPC分类号： G01J3/30

CPC分类号： G01N21/6458 ,  G01N1/36 ,  G01N15/1434 ,  G01N2201/104 ,  G01N2201/1045 ,  G01N2201/112 ,  G02B21/26 ,  G02B21/365

摘要： Detection of a rarely occurring event within one or more biological samples includes (a) processing each biological sample to provide a gellable liquid solution comprising concentrated biological sample and a flourochrome designed to associate with a rarely occurring event within the concentrated biological sample; (b) depositing the solution in a layer on a surface of a slide; and (c) scanning the solution on the slide with energy adapted to cause fluorescence of the flourochrome to detect potential instances of the rarely occurring event within the concentrated biological sample in the solution.

摘要翻译： 在一个或多个生物样品中检测到很少发生的事件包括（a）处理每个生物样品以提供包含浓缩的生物样品和设计成与浓缩的生物样品中罕见事件相关的荧光染料的可胶凝液体溶液; （b）将溶液沉积在载玻片表面上的层中; 和（c）用适于引起荧光色素的能量扫描载玻片上的溶液以检测溶液中浓缩的生物样品内很少发生的事件的潜在情况。

公开(公告)号：US20080036240A1

公开(公告)日：2008-02-14

申请号：US11782083

申请日：2007-07-24

申请人： Kevin Lusk ,  Kenneth Church ,  William Stanton

发明人： Kevin Lusk ,  Kenneth Church ,  William Stanton

IPC分类号： B60R27/00

CPC分类号： B62D31/02 ,  B60R16/0207 ,  B62D27/026 ,  B62D29/043 ,  Y10T403/7152 ,  Y10T428/19

摘要： A vehicle primarily a mass transit vehicle is formed primarily of composite materials which define a roof section and a floor section of two fiber reinforced sheets connected by an integral core and two rigid side wall sections each formed from welded steel or optionally bolted aluminum defining a series of window openings in a row along the side wall section in a ladder shape. The separate sections are connected to a front end cap and a rear end cap. Mountings for the seats are defined as well as conduits through the floor and roof for electrical and fluid connections. Releasable joints of adhesive are provided between the metal rails and the edges of the composite panels.

摘要翻译： 主要是公共交通工具的车辆主要由复合材料形成，所述复合材料限定了由整体铁芯连接的两个纤维增强板的两个纤维增强板的两个纤维增强板和两个刚性侧壁部分的地板部分，所述两个刚性侧壁部分由焊接钢或可选择的螺栓铝形成， 的窗口沿着侧壁部分呈梯形。 分离的部分连接到前端盖和后端盖。 定义座椅的安装以及通过地板和屋顶的电气和液体连接的导管。 在金属轨道和复合板的边缘之间设置粘合剂的可释放接头。

公开(公告)号：US20070168469A1

公开(公告)日：2007-07-19

申请号：US11333486

申请日：2006-01-17

申请人： Kenneth Church ,  Timothy Sharpe ,  Bo Thiesson

发明人： Kenneth Church ,  Timothy Sharpe ,  Bo Thiesson

IPC分类号： G06F15/16

CPC分类号： G06F17/3097 ,  G06F17/273 ,  G06F17/276 ,  Y10S707/99935

摘要： The claimed subject matter provides systems and/or methods that expand input data. An interface can obtain input data and a wildcard insertion component can modify the input data to include at least one implicit wildcard inserted at an end of each intended word. Additionally, an expansion component can generate a candidate list of expanded data based at least in part on the input data including the at least one implicit wildcard utilizing a language model that provides likely expansions of wildcards. Further, the expansion component can evaluate the input data at a server side.

摘要翻译： 所要求保护的主题提供扩展输入数据的系统和/或方法。 接口可以获得输入数据，并且通配符插入组件可以修改输入数据以包括插入每个预期单词末尾的至少一个隐式通配符。 此外，扩展组件可以至少部分地基于包括至少一个隐式通配符的输入数据来生成扩展数据的候选列表，该语言模型提供可能扩展通配符的语言模型。 此外，扩展组件可以评估服务器端的输入数据。

公开(公告)号：US4397561A

公开(公告)日：1983-08-09

申请号：US262754

申请日：1981-05-11

申请人： William A. Strong ,  Kenneth Church

发明人： William A. Strong ,  Kenneth Church

IPC分类号： B01F3/12 ,  B01F15/00 ,  B01F15/04 ,  B65G53/30 ,  G05D24/00

CPC分类号： B01F15/00155 ,  B01F15/00201 ,  B01F15/00246 ,  B01F15/0408 ,  B65G53/30 ,  G05D24/02 ,  B01F2003/125

摘要： A slurry mixing and pumping system adapted to automatically control both slurry viscosity and product output volume. Water and raw gypsum delivered to a mixing vat are thoroughly blended by a hydraulically powered agitator blade within the vat. Hydraulic pressure variations experienced by the agitator motor are translated into pneumatic viscosity control signals by a process controller. An air actuated water valve driven by the controller varies water input into the vat to effectuate viscosity correction. Means responsive to vat head level controls output volume.

摘要翻译： 浆料混合和泵送系统适用于自动控制浆液粘度和产品输出量。 送到混合桶中的水和原料石膏通过桶内的液压动力搅拌器叶片充分混合。 搅拌马达经历的液压变化由过程控制器转化为气动粘度控制信号。 由控制器驱动的空气致动水阀将输入大桶的水变化，以实现粘度校正。 响应桶头水平控制输出量的方法。

公开(公告)号：US20090083214A1

公开(公告)日：2009-03-26

申请号：US11858920

申请日：2007-09-21

申请人： Arnd C. Konig ,  Surajit Chaudhuri ,  Kenneth Church ,  Liying Sui

发明人： Arnd C. Konig ,  Surajit Chaudhuri ,  Kenneth Church ,  Liying Sui

IPC分类号： G06F17/30

CPC分类号： G06F16/3331 ,  G06F16/313

摘要： Index structures and query processing framework that enforces a given threshold on the overhead of computing conjunctive keyword queries. This includes a keyword processing algorithm, logic to determine which indexes to materialize, and a probabilistic approach to reducing the overhead for determining which indexes to build. The index structures leverage the fact that the frequency distribution of natural-language text follows a power law. Given a document collection, a set of indexes is proposed for materialization so that the time for intersecting keywords does not exceed a given threshold Δ. When considering the associated space requirement, the additional indexes are limited. Materialization of such a set of indexes for reasonable values of Δ (e.g., the time required to scan 20% of the largest inverted index), at least for a collection of short documents is distributed by the power law.

摘要翻译： 索引结构和查询处理框架，其对计算关键词查询的开销执行给定的阈值。 这包括关键字处理算法，确定要实现哪些索引的逻辑，以及减少用于确定构建哪些索引的开销的概率方法。 指数结构利用了自然语言文本的频率分布遵循幂律的事实。 给定文档集合，提出了一组索引用于实现，以便关键字相交的时间不超过给定的阈值Delta。 在考虑相关空间需求时，附加指标有限。 对于合理的Delta值（例如，扫描20％的最大倒排指数所需的时间），至少对于短文件的收集，这种一组索引的实现是通过权力法分配的。

公开(公告)号：US20070164782A1

公开(公告)日：2007-07-19

申请号：US11332954

申请日：2006-01-17

申请人： Kenneth Church ,  Timothy Sharpe ,  Bo Thiesson

发明人： Kenneth Church ,  Timothy Sharpe ,  Bo Thiesson

IPC分类号： H03K19/177

CPC分类号： G06F17/276

摘要： The claimed subject matter provides systems and/or methods that expand input data. An interface can obtain input data and a wildcard insertion component can modify the input data to include at least one implicit wildcard inserted at an end of each intended word. Additionally, an expansion component can generate a candidate list of expanded data based at least in part on the input data including the at least one implicit wildcard utilizing a language model that provides likely expansions of wildcards. Further, the expansion component can evaluate the input data at a server side.

摘要翻译： 所要求保护的主题提供扩展输入数据的系统和/或方法。 接口可以获得输入数据，并且通配符插入组件可以修改输入数据以包括插入每个预期单词末尾的至少一个隐式通配符。 此外，扩展组件可以至少部分地基于包括至少一个隐式通配符的输入数据来生成扩展数据的候选列表，该语言模型提供可能扩展通配符的语言模型。 此外，扩展组件可以评估服务器端的输入数据。