-
公开(公告)号：US09224388B2
公开(公告)日：2015-12-29
申请号：US13371966
申请日：2012-02-13
申请人： Kisun You , Kyu Woong Hwang , Taesu Kim
发明人： Kisun You , Kyu Woong Hwang , Taesu Kim
CPC分类号： G10L15/08
摘要： A method for generating an anti-model of a sound class is disclosed. A plurality of candidate sound data is provided for generating the anti-model. A plurality of similarity values between the plurality of candidate sound data and a reference sound model of a sound class is determined. An anti-model of the sound class is generated based on at least one candidate sound data having the similarity value within a similarity threshold range.
摘要翻译： 公开了一种用于产生声级的反模型的方法。 多个候选声音数据被提供用于产生反模型。 确定多个候选声音数据与声音类别的参考声音模型之间的多个相似度值。 基于具有相似性阈值范围内的相似度值的至少一个候选声音数据，生成声音类别的反模型。
-
公开(公告)号：US09443511B2
公开(公告)日：2016-09-13
申请号：US13285971
申请日：2011-10-31
申请人： Kyu Woong Hwang , Taesu Kim , Kisun You
发明人： Kyu Woong Hwang , Taesu Kim , Kisun You
摘要： A method for recognizing an environmental sound in a client device in cooperation with a server is disclosed. The client device includes a client database having a plurality of sound models of environmental sounds and a plurality of labels, each of which identifies at least one sound model. The client device receives an input environmental sound and generates an input sound model based on the input environmental sound. At the client device, a similarity value is determined between the input sound model and each of the sound models to identify one or more sound models from the client database that are similar to the input sound model. A label is selected from labels associated with the identified sound models, and the selected label is associated with the input environmental sound based on a confidence level of the selected label.
摘要翻译： 公开了一种与服务器协作来识别客户端设备中的环境声音的方法。 客户端设备包括具有环境声音的多个声音模型的客户数据库和多个标签，每个标签识别至少一个声音模型。 客户端设备接收输入环境声音，并根据输入的环境声音生成输入声音模型。 在客户机设备处，在输入声音模型和每个声音模型之间确定相似性值，以从客户端数据库识别类似于输入声音模型的一个或多个声音模型。 从与识别的声音模型相关联的标签中选择标签，并且所选择的标签基于所选标签的置信水平与输入的环境声音相关联。
-
公开(公告)号：US09349066B2
公开(公告)日：2016-05-24
申请号：US13567412
申请日：2012-08-06
申请人： Hyung-Il Koo , Kisun You , Young-Ki Baik
发明人： Hyung-Il Koo , Kisun You , Young-Ki Baik
CPC分类号： G06K9/3258 , G06K9/00664 , G06K9/00671 , G06K9/325 , G06K2209/01
摘要： A method includes tracking an object in each of a plurality of frames of video data to generate a tracking result. The method also includes performing object processing of a subset of frames of the plurality of frames selected according to a multi-frame latency of an object detector or an object recognizer. The method includes combining the tracking result with an output of the object processing to produce a combined output.
摘要翻译： 一种方法包括跟踪视频数据的多个帧中的每一个中的对象以产生跟踪结果。 该方法还包括执行根据对象检测器或对象识别器的多帧等待时间选择的多个帧的帧的子集的对象处理。 该方法包括将跟踪结果与对象处理的输出组合以产生组合输出。
-
公开(公告)号：US08942484B2
公开(公告)日：2015-01-27
申请号：US13412853
申请日：2012-03-06
申请人： Hyung-Il Koo , Kisun You
发明人： Hyung-Il Koo , Kisun You
CPC分类号： G06K9/3258 , G06K9/3275 , G06K9/4652 , G06K2209/01
摘要： A method includes receiving an indication of a set of image regions identified in image data. The method further includes, selecting image regions from the set of image regions for text extraction at least partially based on image region stability.
摘要翻译： 一种方法包括接收在图像数据中标识的一组图像区域的指示。 该方法还包括：至少部分地基于图像区域稳定性从用于文本提取的图像区域集合中选择图像区域。
-
公开(公告)号：US20130058575A1
公开(公告)日：2013-03-07
申请号：US13412853
申请日：2012-03-06
申请人： HYUNG-IL KOO , Kisun You
发明人： HYUNG-IL KOO , Kisun You
IPC分类号： G06K9/34
CPC分类号： G06K9/3258 , G06K9/3275 , G06K9/4652 , G06K2209/01
摘要： A method includes receiving an indication of a set of image regions identified in image data. The method further includes, selecting image regions from the set of image regions for text extraction at least partially based on image region stability.
摘要翻译： 一种方法包括接收在图像数据中标识的一组图像区域的指示。 该方法还包括：至少部分地基于图像区域稳定性从用于文本提取的图像区域集合中选择图像区域。
-
公开(公告)号：US08484154B2
公开(公告)日：2013-07-09
申请号：US12637228
申请日：2009-12-14
申请人： Kisun You , Christopher J. Hughes , Yen-Kuang Chen
发明人： Kisun You , Christopher J. Hughes , Yen-Kuang Chen
IPC分类号： G06N7/02
CPC分类号： G10L15/063 , G10L15/02 , G10L15/083 , G10L15/19 , G10L15/34
摘要： Methods and systems to translate input labels of arcs of a network, corresponding to a sequence of states of the network, to a list of output grammar elements of the arcs, corresponding to a sequence of grammar elements. The network may include a plurality of speech recognition models combined with a weighted finite state machine transducer (WFST). Traversal may include active arc traversal, and may include active arc propagation. Arcs may be processed in parallel, including arcs originating from multiple source states and directed to a common destination state. Self-loops associated with states may be modeled within outgoing arcs of the states, which may reduce synchronization operations. Tasks may be ordered with respect to cache-data locality to associate tasks with processing threads based at least in part on whether another task associated with a corresponding data object was previously assigned to the thread.
摘要翻译： 将对应于网络状态序列的网络的弧的输入标签转换成对应于语法元素序列的弧的输出语法元素的列表的方法和系统。 网络可以包括与加权的有限状态机换能器（WFST）组合的多个语音识别模型。 遍历可能包括有效的电弧遍历，并且可能包括有效的电弧传播。 弧可以并行处理，包括源自多个源状态并被引导到公共目的地状态的弧。 与状态相关联的自环可以在状态的输出弧内被建模，这可以减少同步操作。 至少部分地基于是否将与对应的数据对象相关联的另一个任务先前分配给线程，可以针对高速缓存数据位置命令任务来将任务与处理线程相关联。
-
公开(公告)号：US20140156274A1
公开(公告)日：2014-06-05
申请号：US13925150
申请日：2013-06-24
申请人： Kisun You , Christopher J. Hughes , Yen-Kuang Chen
发明人： Kisun You , Christopher J. Hughes , Yen-Kuang Chen
CPC分类号： G10L15/063 , G06N7/005 , G10L15/02 , G10L15/083 , G10L15/19 , G10L15/34
摘要： Methods and systems to translate input labels of arcs of a network, corresponding to a sequence of states of the network, to a list of output grammar elements of the arcs, corresponding to a sequence of grammar elements. The network may include a plurality of speech recognition models combined with a weighted finite state machine transducer (WFST). Traversal may include active arc traversal, and may include active arc propagation. Arcs may be processed in parallel, including arcs originating from multiple source states and directed to a common destination state. Self-loops associated with states may be modeled within outgoing arcs of the states, which may reduce synchronization operations. Tasks may be ordered with respect to cache-data locality to associate tasks with processing threads based at least in part on whether another task associated with a corresponding data object was previously assigned to the thread.
摘要翻译： 将对应于网络状态序列的网络的弧的输入标签转换成对应于语法元素序列的弧的输出语法元素的列表的方法和系统。 网络可以包括与加权的有限状态机换能器（WFST）组合的多个语音识别模型。 遍历可能包括有效的电弧遍历，并且可能包括有效的电弧传播。 弧可以并行处理，包括源自多个源状态并被引导到公共目的地状态的弧。 与状态相关联的自环可以在状态的输出弧内被建模，这可以减少同步操作。 至少部分地基于是否将与对应的数据对象相关联的另一个任务先前分配给线程，可以针对高速缓存数据位置命令任务来将任务与处理线程相关联。
-
公开(公告)号：US20130177203A1
公开(公告)日：2013-07-11
申请号：US13567412
申请日：2012-08-06
申请人： Hyung-Il Koo , Kisun You , Young-Ki Baik
发明人： Hyung-Il Koo , Kisun You , Young-Ki Baik
IPC分类号： G06K9/00
CPC分类号： G06K9/3258 , G06K9/00664 , G06K9/00671 , G06K9/325 , G06K2209/01
摘要： A method includes tracking an object in each of a plurality of frames of video data to generate a tracking result. The method also includes performing object processing of a subset of frames of the plurality of frames selected according to a multi-frame latency of an object detector or an object recognizer. The method includes combining the tracking result with an output of the object processing to produce a combined output.
摘要翻译： 一种方法包括跟踪视频数据的多个帧中的每一个中的对象以产生跟踪结果。 该方法还包括执行根据对象检测器或对象识别器的多帧等待时间选择的多个帧的帧的子集的对象处理。 该方法包括将跟踪结果与对象处理的输出组合以产生组合输出。
-
公开(公告)号：US20110145184A1
公开(公告)日：2011-06-16
申请号：US12637228
申请日：2009-12-14
申请人： Kisun You , Christopher J. Hughes , Yen-Kuang Chen
发明人： Kisun You , Christopher J. Hughes , Yen-Kuang Chen
CPC分类号： G10L15/063 , G10L15/02 , G10L15/083 , G10L15/19 , G10L15/34
摘要： Methods and systems to translate input labels of arcs of a network, corresponding to a sequence of states of the network, to a list of output grammar elements of the arcs, corresponding to a sequence of grammar elements. The network may include a plurality of speech recognition models combined with a weighted finite state machine transducer (WFST). Traversal may include active arc traversal, and may include active arc propagation. Arcs may be processed in parallel, including arcs originating from multiple source states and directed to a common destination state. Self-loops associated with states may be modeled within outgoing arcs of the states, which may reduce synchronization operations. Tasks may be ordered with respect to cache-data locality to associate tasks with processing threads based at least in part on whether another task associated with a corresponding data object was previously assigned to the thread.
摘要翻译： 将对应于网络状态序列的网络的弧的输入标签转换成对应于语法元素序列的弧的输出语法元素的列表的方法和系统。 网络可以包括与加权的有限状态机换能器（WFST）组合的多个语音识别模型。 遍历可能包括有效的电弧遍历，并且可能包括有效的电弧传播。 弧可以并行处理，包括源自多个源状态并被引导到公共目的地状态的弧。 与状态相关联的自环可以在状态的输出弧内被建模，这可以减少同步操作。 至少部分地基于是否将与对应的数据对象相关联的另一个任务先前分配给线程，可以针对高速缓存数据位置命令任务来将任务与处理线程相关联。
-
-
-
-
-
-
-
-
搜索结果
29 条记录 (耗时 0.03 秒)
