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

US09099093B2 Apparatus and method of improving intelligibility of voice signal 有权
标题翻译：提高语音信号清晰度的装置和方法
公开(公告)号：US09099093B2
公开(公告)日：2015-08-04
申请号：US11984421
申请日：2007-11-16
申请人： Chang-kyu Choi , Kwang-il Hwang , Sun-gi Hong , Young-hun Sung , Yeun-bae Kim , Yong Kim , Sang-hoon Lee , Hong Jeong
发明人： Chang-kyu Choi , Kwang-il Hwang , Sun-gi Hong , Young-hun Sung , Yeun-bae Kim , Yong Kim , Sang-hoon Lee , Hong Jeong
IPC分类号： G10L21/00 , G10L21/02 , G10L25/93 , G10L21/0208 , G10L21/0364 , G10L25/78 , G10L25/90
CPC分类号： G10L21/0208 , G10L21/0364 , G10L25/78 , G10L25/90
摘要： The present invention relates to an apparatus and method of improving intelligibility of a voice signal. A method of improving intelligibility of a voice signal according to an embodiment of the present invention includes analyzing a background noise signal on a call receiving side, classifying a received voice signal into a silence signal, an unvoiced sound signal, and a voiced sound signal, and intensifying the classified unvoiced sound signal and voiced sound signal on the basis of the analyzed background noise signal on the call receiving side.
摘要翻译：本发明涉及提高语音信号的可懂度的装置和方法。根据本发明的实施例的提高语音信号的可懂度的方法包括分析呼叫接收侧的背景噪声信号，将接收的语音信号分类为静音信号，无声声音信号和浊音信号，基于呼叫接收侧的分析背景噪声信号，加强分类的无声声音信号和浊音信号。

2. 发明授权

US07483530B2 Apparatus for separating blind source signals having systolic array structure 失效
标题翻译：用于分离具有收缩阵列结构的盲源信号的装置
公开(公告)号：US07483530B2
公开(公告)日：2009-01-27
申请号：US10989430
申请日：2004-11-17
申请人： Hong Jeong , Yong Kim
发明人： Hong Jeong , Yong Kim
IPC分类号： H04M9/08
CPC分类号： G10L21/028 , G06K9/624
摘要： Disclosed is a hardware architecture receiving multi-input blind source signals and obtaining multi-output. An apparatus for separating blind source signals includes: a forward process unit receiving a plurality of blind source signal vectors and outputting a plurality of output signal vectors by using a predetermined blind source separation algorithm; an update process unit receiving the plurality of output signal vectors and learning first weighting values used for the predetermined blind source separation algorithm according to a predetermined learning algorithm; and a weight process unit having a matrix operation structure for receiving the first weighting values and converting them into coefficients and second weighting values applicable to the predetermined blind source separation algorithm. The forward process unit includes (L+1) identical processing elements connected in a systolic array structure, where L is the number of sequential delay of blind input signal vectors. The update process unit includes (N2+N)/2×(2L+1) identical updating elements connected in a systolic array structure, where N is the number of the blind input signal vectors. Each cost of the processing elements and the updating elements is initialized by 0 in an initial operation stage.
摘要翻译：公开了一种接收多输入盲源信号并获得多输出的硬件架构。一种用于分离盲源信号的装置包括：前向处理单元，接收多个盲源信号向量，并通过使用预定的盲源分离算法输出多个输出信号向量; 更新处理单元，根据预定的学习算法，接收多个输出信号矢量和学习用于预定盲源分离算法的第一加权值; 以及加权处理单元，具有用于接收第一加权值并将其转换成适用于预定盲源分离算法的系数和第二加权值的矩阵运算结构。前向处理单元包括（L + 1）以脉冲阵列结构连接的相同的处理元件，其中L是盲输入信号矢量的顺序延迟的数量。更新处理单元包括连接在收缩阵列结构中的（N2 + N）/ 2x（2L + 1）相同的更新元件，其中N是盲输入信号矢量的数量。在初始操作阶段，处理元件和更新元件的每个成本被初始化为0。

3. 发明申请

US20080167863A1 Apparatus and method of improving intelligibility of voice signal 有权
标题翻译：提高语音信号清晰度的装置和方法
公开(公告)号：US20080167863A1
公开(公告)日：2008-07-10
申请号：US11984421
申请日：2007-11-16
申请人： Chang-kyu Choi , Kwang-il Hwang , Sun-gi Hong , Young-hun Sung , Yeun-bae Kim , Yong Kim , Sang-hoon Lee , Hong Jeong
发明人： Chang-kyu Choi , Kwang-il Hwang , Sun-gi Hong , Young-hun Sung , Yeun-bae Kim , Yong Kim , Sang-hoon Lee , Hong Jeong
IPC分类号： G10L11/06 , G10L21/00 , G10L15/00
CPC分类号： G10L21/0208 , G10L21/0364 , G10L25/78 , G10L25/90
摘要： The present invention relates to an apparatus and method of improving intelligibility of a voice signal. A method of improving intelligibility of a voice signal according to an embodiment of the present invention includes analyzing a background noise signal on a call receiving side, classifying a received voice signal into a silence signal, an unvoiced sound signal, and a voiced sound signal, and intensifying the classified unvoiced sound signal and voiced sound signal on the basis of the analyzed background noise signal on the call receiving side.
摘要翻译：本发明涉及提高语音信号的可懂度的装置和方法。根据本发明的实施例的提高语音信号的可懂度的方法包括分析呼叫接收侧的背景噪声信号，将接收的语音信号分类为静音信号，无声声音信号和浊音信号，基于呼叫接收侧的分析背景噪声信号，加强分类的无声声音信号和浊音信号。

4. 发明申请

US20060235686A1 Speech recognition device 审中-公开
标题翻译：语音识别装置
公开(公告)号：US20060235686A1
公开(公告)日：2006-10-19
申请号：US11262167
申请日：2005-10-28
申请人： Hong Jeong , Yong Kim
发明人： Hong Jeong , Yong Kim
IPC分类号： G10L15/00
CPC分类号： G10L15/32 , G10L15/20 , G10L21/0208
摘要： Disclosed is a speech recognition device using a hidden Markov model and a two-level dynamic programming scheme. The speech recognition device includes an analog to digital converter for sampling and quantizing speech signals into digital speech signals; a noise eliminator for reducing noise from the digital speech signals; a feature vector generator for generating a feature vector from the noise-eliminated speech signals, and converting the feature vector into a test pattern; and a processor including a plurality of processing elements arranged in parallel, each processing element calculating a matching cost of a test pattern and a reference pattern, selecting the minimum value from among the calculated matching costs, and outputting the minimum value as the minimum matching cost of an input test pattern.
摘要翻译：公开了一种使用隐马尔可夫模型和两级动态规划方案的语音识别装置。语音识别装置包括用于将语音信号采样和量化成数字语音信号的模数转换器; 用于减少来自数字语音信号的噪声的噪声消除器; 特征向量生成器，用于从噪声消除的语音信号生成特征向量，并将特征向量转换成测试图案; 以及处理器，包括并行布置的多个处理元件，每个处理元件计算测试图案和参考图案的匹配成本，从所计算的匹配成本中选择最小值，并输出最小值作为最小匹配成本的输入测试图案。

5. 发明申请

US20060095258A1 Apparatus for separating blind source signals having systolic array structure 失效
标题翻译：用于分离具有收缩阵列结构的盲源信号的装置
公开(公告)号：US20060095258A1
公开(公告)日：2006-05-04
申请号：US10989430
申请日：2004-11-17
申请人： Hong Jeong , Yong Kim
发明人： Hong Jeong , Yong Kim
IPC分类号： G10L15/20
CPC分类号： G10L21/028 , G06K9/624
摘要： Disclosed is a hardware architecture receiving multi-input blind source signals and obtaining multi-output. An apparatus for separating blind source signals includes: a forward process unit receiving a plurality of blind source signal vectors and outputting a plurality of output signal vectors by using a predetermined blind source separation algorithm; an update process unit receiving the plurality of output signal vectors and learning first weighting values used for the predetermined blind source separation algorithm according to a predetermined learning algorithm; and a weight process unit having a matrix operation structure for receiving the first weighting values and converting them into coefficients and second weighting values applicable to the predetermined blind source separation algorithm. The forward process unit includes (L+1) identical processing elements connected in a systolic array structure, where L is the number of sequential delay of blind input signal vectors. The update process unit includes (N2+N)/2×(2L+1) identical updating elements connected in a systolic array structure, where N is the number of the blind input signal vectors. Each cost of the processing elements and the updating elements is initialized by 0 in an initial operation stage.
摘要翻译：公开了一种接收多输入盲源信号并获得多输出的硬件架构。一种用于分离盲源信号的装置包括：前向处理单元，接收多个盲源信号向量，并通过使用预定的盲源分离算法输出多个输出信号向量; 更新处理单元，根据预定的学习算法，接收多个输出信号矢量和学习用于预定盲源分离算法的第一加权值; 以及加权处理单元，具有用于接收第一加权值并将其转换成适用于预定盲源分离算法的系数和第二加权值的矩阵运算结构。前向处理单元包括（L + 1）以脉冲阵列结构连接的相同的处理元件，其中L是盲输入信号矢量的顺序延迟的数量。更新处理单元包括以收缩阵列结构连接的（N 2+ N +）/ 2x（2L + 1）相同的更新元件，其中N是盲输入信号矢量的数量。在初始操作阶段，处理元件和更新元件的每个成本被初始化为0。

6. 发明授权

US07143034B2 Dynamic time warping device for detecting a reference pattern having a smallest matching cost value with respect to a test pattern, and speech recognition apparatus using the same 失效
标题翻译：用于检测相对于测试图案具有最小匹配成本值的参考图案的动态时间扭曲装置，以及使用该参考图案的语音识别装置
公开(公告)号：US07143034B2
公开(公告)日：2006-11-28
申请号：US10277978
申请日：2002-10-23
申请人： Hong Jeong , Yong Kim
发明人： Hong Jeong , Yong Kim
IPC分类号： G10L15/12
CPC分类号： G10L15/12
摘要： Provided are a dynamic time warping device using speech recognition software, and a speech recognition apparatus using the same. The dynamic time warping device includes memory units for processing characterization vectors of a test pattern and a predetermined reference pattern using a FIFO queue, and a plurality of processing elements serially connected to each other, the plurality of processing elements multiplying a predetermined weight by a difference between the characterization vectors of the test and reference patterns, which are obtained by shifting them in the opposite directions, adding the multiplication result to matching cost values of adjacent nodes, and comparing the addition results to detect the smallest matching cost value. Accordingly, fast speech recognition can be realized by embedding speech recognition software using a dynamic time warping algorithm into hardware. Also, it is possible to increase a recognition rate of speech by adjusting weight according to a node to be compared, and provide a dynamic time warping device that can be mass-produced as application-specification integrated circuits (ASICs). Further, a compact speech recognition apparatus using the dynamic time warping device can be provided without requiring a computer to drive software for speech recognition.
摘要翻译：提供了一种使用语音识别软件的动态时间扭曲装置和使用其的语音识别装置。动态时间扭曲装置包括用于处理测试图案的特征向量和使用FIFO队列的预定参考图案的存储单元和多个串联连接的处理元件，所述多个处理元件将预定权重乘以差在通过相反方向移位而获得的测试和参考图案的表征向量之间，将相乘结果相加到相邻节点的匹配成本值，并比较加法结果以检测最小匹配成本值。因此，可以通过使用动态时间扭曲算法将语音识别软件嵌入硬件来实现快速语音识别。此外，通过根据要比较的节点调整权重，可以提高语音的识别率，并且提供可以作为应用规范集成电路（ASIC）批量生产的动态时间整经装置。此外，可以提供使用动态时间扭曲装置的紧凑型语音识别装置，而不需要计算机来驱动用于语音识别的软件。

7. 发明授权

US08427524B2 Message propagation-based stereo image matching system 有权
标题翻译：基于消息传播的立体图像匹配系统
公开(公告)号：US08427524B2
公开(公告)日：2013-04-23
申请号：US12312246
申请日：2007-10-30
申请人： Hong Jeong , Sung Chan Park
发明人： Hong Jeong , Sung Chan Park
IPC分类号： H04N15/00
CPC分类号： G06K9/32 , G06T7/593 , H04N13/10
摘要： A stereo image matching system includes an image processing unit for converting input images inputted from a first and a second image acquisition unit into digital signals to output first and second pixel data; and an image matching unit for computing at least two of an upward, a downward, a forward and a backward message of each pixel by using data values of the first and the second pixel data that are located on a same epipolar line to calculate a disparity value of each pixel by using the computed messages corresponding to adjacent pixel(s). The stereo image matching system employs a parallel pipeline VLSI configuration with a time complexity of O(N). Thus, a plurality of image lines are used for matching, so that correct distance image information is obtained regardless of the conditions of the surrounding environment.
摘要翻译：立体图像匹配系统包括图像处理单元，用于将从第一和第二图像获取单元输入的输入图像转换为数字信号以输出第一和第二像素数据; 以及图像匹配单元，用于通过使用位于同一对极线上的第一和第二像素数据的数据值来计算每个像素的向上，向下，向前和向后的消息中的至少两个来计算视差通过使用与相邻像素相对应的计算消息的每个像素的值。立体图像匹配系统采用时间复杂度为O（N）的并行流水线VLSI配置。因此，使用多个图像线进行匹配，从而获得正确的距离图像信息，而不管周围环境的条件如何。

8. 发明授权

US07590281B2 Stereo image matching method and system using image multiple lines 失效
标题翻译：立体图像匹配方法和系统使用图像多行
公开(公告)号：US07590281B2
公开(公告)日：2009-09-15
申请号：US11032253
申请日：2005-01-10
申请人： Hong Jeong , Sungchan Park
发明人： Hong Jeong , Sungchan Park
IPC分类号： G06K9/00
CPC分类号： G06T7/593
摘要： Disclosed is a stereo image matching method for re-creating 3-dimensional spatial information from a pair of 2-dimensional images. The conventional stereo image matching method generates much noise from a disparity value in the vertical direction, but the present invention uses disparity information of adjacent image lines as a constraint condition to eliminate the noise in the vertical direction, and compress the disparity by using a differential coding method to thereby increase a compression rate.
摘要翻译：公开了一种用于从一对二维图像重建三维空间信息的立体图像匹配方法。常规立体图像匹配方法从垂直方向上的视差值产生大量噪声，但是本发明使用相邻图像线的视差信息作为约束条件来消除垂直方向上的噪声，并且通过使用差分从而提高压缩率。

9. 发明授权

US09390507B2 Apparatus and method for hierarchical stereo matching 有权
标题翻译：分层立体匹配的装置和方法
公开(公告)号：US09390507B2
公开(公告)日：2016-07-12
申请号：US14359537
申请日：2012-07-04
申请人： Junseo Lee , Jeongmok Ha , Intae Na , Hong Jeong
发明人： Junseo Lee , Jeongmok Ha , Intae Na , Hong Jeong
IPC分类号： G06T7/00
CPC分类号： G06T7/0075 , G06T7/593 , G06T2207/10012 , G06T2207/10021 , G06T2207/20016
摘要： An apparatus and a method for hierarchical stereo matching are provided. In the method, a reduced image is formed by reducing left and right images, and a first Trellis is performed on the reduced image. Then, a magnified image is generated by magnifying the size and the brightness of the reduced image, and a second Trellis is performed on the magnified image.
摘要翻译：提供了一种用于分级立体匹配的装置和方法。在该方法中，通过减小左图像和右图像来形成缩小图像，并且对缩小图像执行第一格子。然后，通过放大缩小图像的大小和亮度来生成放大图像，并且对放大图像执行第二格子。

10. 发明申请

US20110026809A1 Fast multi-view three-dimensional image synthesis apparatus and method 审中-公开
标题翻译：快速多视图三维图像合成装置及方法
公开(公告)号：US20110026809A1
公开(公告)日：2011-02-03
申请号：US12923820
申请日：2010-10-08
申请人： Hong Jeong , Jang Myoung Kim , Sung Chan Park
发明人： Hong Jeong , Jang Myoung Kim , Sung Chan Park
IPC分类号： G06K9/00
CPC分类号： G06T7/97 , G06T2207/10021 , G06T2207/20228 , H04N13/111
摘要： A fast multi-view three-dimensional image synthesis apparatus includes: a disparity map generation module for generating a left image disparity map by using left and right image pixel data; intermediate-view generation modules for generating intermediate-view pixel data from different view points by using the left and right image pixel data and the left image disparity map; and a multi-view three-dimensional image generation module for generating multi-view three-dimensional image pixel data by using the left image pixel data, the right image pixel data and intermediate-view pixel data. Each of the intermediate-view generation module includes: a right image disparity map generation unit for generating a rough right image disparity map; an occluded region compensation unit for generating a right image disparity map by removing occluded regions from the rough right image disparity map; and an intermediate-view generation unit for generating the intermediate-view pixel data from the different view points.
摘要翻译：快速多视图三维图像合成装置包括：视差图生成模块，用于通过使用左图像像素数据和右图像像素数据生成左图像视差图; 中间视图生成模块，用于通过使用左图像像素数据和左图像像素数据和左图像视差图从不同视点生成中间视点像素数据; 以及用于通过使用左图像像素数据，右图像像素数据和中间像素数据来生成多视图三维图像像素数据的多视图三维图像生成模块。每个中间视图生成模块包括：右图像视差图生成单元，用于生成粗略的右图像视差图; 闭塞区域补偿单元，用于通过从粗略右图像视差图去除遮挡区域来产生右图像视差图; 以及用于从不同观点生成中间视点像素数据的中间视图生成单元。

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