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. 发明专利

HK1045016B 聲音相似性量度未知
公开(公告)号：HK1045016B
公开(公告)日：2010-11-12
申请号：HK02106431
申请日：2002-08-30
申请人： MICHIHIRO JINNAI
发明人： JINNAI MICHIHIRO , YAMAGUCHI HIROSHI
IPC分类号： G10L20060101 , G01H17/00 , G06K20060101 , G06K9/62 , G06T7/00 , G06T7/20 , G10L15/06 , G10L15/10 , G10L15/20

2. 发明专利

HK1045016A1 VOICES SIMILARITY MEASUREMENT 未知
公开(公告)号：HK1045016A1
公开(公告)日：2002-11-08
申请号：HK02106431
申请日：2002-08-30
申请人： MICHIHIRO JINNAI
发明人： JINNAI MICHIHIRO , YAMAGUCHI HIROSHI
IPC分类号： G01H17/00 , G06K20060101 , G06K9/62 , G06T7/00 , G06T7/20 , G10L20060101 , G10L15/06 , G10L15/10 , G10L15/20

3. 发明授权

US09552831B2 Method for detecting abnormal sound and method for judging abnormality in structure by use of detected value thereof, and method for detecting similarity between oscillation waves and method for recognizing voice by use of detected value thereof 有权
标题翻译：用于检测异常声音的方法和使用其检测值来判断结构异常的方法以及用于检测振荡波之间的相似度的方法和通过使用其检测值来识别语音的方法
公开(公告)号：US09552831B2
公开(公告)日：2017-01-24
申请号：US15003376
申请日：2016-01-21
申请人： WEST NIPPON EXPRESSWAY ENGINEERING SHIKOKU COMPANY LIMITED , Michihiro Jinnai
发明人： Michihiro Jinnai , Yukio Akashi , Kazuaki Hashimoto , Shogo Hayashi
IPC分类号： G10L25/84 , G10L25/51 , G10L25/87 , G10L25/18 , G10L21/0388 , G10L15/10 , G10L17/08
CPC分类号： G10L25/84 , G10L15/10 , G10L17/08 , G10L21/0388 , G10L25/03 , G10L25/18 , G10L25/51 , G10L25/87
摘要： The present invention provides a method for obtaining an accurate detected value of a similarity, such as an hitting sound. The method includes the steps of: creating original standard/input pattern vectors each having a feature quantity of an hitting sound; creating a skewness-weighting vector and a kurtosis-weighting vector based on a reference pattern vector of a reference shape; calculating a skewness-weighted standard pattern vector and a kurtosis-weighted standard pattern vector by product-sum operation using component values of the skewness-weighting vector and the kurtosis-weighting vector and a component value of the original standard pattern vector; creating a dual and weighted standard pattern vector based on these vectors and similarly creating a dual and weighted input pattern vector; creating dual and selected standard/input pattern vectors based on the dual and weighted standard/input pattern vectors; and setting an angle between the dual and selected standard and input pattern vectors as a geometric distance value between the original standard and input pattern vectors.
摘要翻译：本发明提供了一种获得诸如打击声等相似性的精确检测值的方法。该方法包括以下步骤：创建每个具有击打声音的特征量的原始标准/输入图形矢量; 基于参考图形的参考图案向量创建偏度加权矢量和峰度加权矢量; 通过使用偏度加权矢量和峰度加权矢量的分量值和原始标准图案矢量的分量值，通过乘积和运算来计算偏度加权标准模式向量和峰度加权标准模式矢量; 基于这些向量创建双重和加权的标准模式向量，并类似地创建双重和加权的输入模式向量; 基于双重和加权的标准/输入模式向量创建双重和选定的标准/输入模式向量; 并将双重和所选标准和输入图案向量之间的角度设置为原始标准和输入图案向量之间的几何距离值。

4. 发明申请

US20160225389A1 METHOD FOR DETECTING ABNORMAL SOUND AND METHOD FOR JUDGING ABNORMALITY IN STRUCTURE BY USE OF DETECTED VALUE THEREOF, AND METHOD FOR DETECTING SIMILARITY BETWEEN OSCILLATION WAVES AND METHOD FOR RECOGNIZING VOICE BY USE OF DETECTED VALUE THEREOF 有权
标题翻译：用于检测异常声音的方法和通过使用其检测值来判断结构异常的方法，以及用于检测振荡波之间的相似性的方法以及通过使用其检测值来识别语音的方法
公开(公告)号：US20160225389A1
公开(公告)日：2016-08-04
申请号：US15003376
申请日：2016-01-21
申请人： Michihiro JINNAI , WEST NIPPON EXPRESSWAY ENGINEERING SHIKOKU COMPANY LIMITED
发明人： Michihiro JINNAI , Yukio AKASHI , Kazuaki HASHIMOTO , Shogo HAYASHI
IPC分类号： G10L25/84 , G10L21/0388 , G10L25/18 , G10L25/51 , G10L25/87
CPC分类号： G10L25/84 , G10L15/10 , G10L17/08 , G10L21/0388 , G10L25/03 , G10L25/18 , G10L25/51 , G10L25/87
摘要： The present invention provides a method for obtaining an accurate detected value of a similarity, such as an hitting sound. The method includes the steps of: creating original standard/input pattern vectors each having a feature quantity of an hitting sound; creating a skewness-weighting vector and a kurtosis-weighting vector based on a reference pattern vector of a reference shape; calculating a skewness-weighted standard pattern vector and a kurtosis-weighted standard pattern vector by product-sum operation using component values of the skewness-weighting vector and the kurtosis-weighting vector and a component value of the original standard pattern vector; creating a dual and weighted standard pattern vector based on these vectors and similarly creating a dual and weighted input pattern vector; creating dual and selected standard/input pattern vectors based on the dual and weighted standard/input pattern vectors; and setting an angle between the dual and selected standard and input pattern vectors as a geometric distance value between the original standard and input pattern vectors.
摘要翻译：本发明提供了一种获得诸如打击声等相似性的精确检测值的方法。该方法包括以下步骤：创建每个具有击打声音的特征量的原始标准/输入图形矢量; 基于参考图形的参考图案向量创建偏度加权矢量和峰度加权矢量; 通过使用偏度加权矢量和峰度加权矢量的分量值和原始标准图案矢量的分量值，通过乘积和运算来计算偏度加权标准模式向量和峰度加权标准模式矢量; 基于这些向量创建双重和加权的标准模式向量，并类似地创建双重和加权的输入模式向量; 基于双重和加权的标准/输入模式向量创建双重和选定的标准/输入模式向量; 并将双重和所选标准和输入图案向量之间的角度设置为原始标准和输入图案向量之间的几何距离值。

5. 发明授权

US07194133B2 Methods for detecting similarity between images, voices, oscillation waves, moving images, and solids and methods for recovering the image, voice, abnormality in a machine, moving image, and solid by the use of detected value thereof 失效
标题翻译：用于检测图像，声音，振荡波，运动图像和实体之间的相似性的方法以及通过使用其检测值来恢复图像，语音，机器中的异常，运动图像和实体的方法
公开(公告)号：US07194133B2
公开(公告)日：2007-03-20
申请号：US10386662
申请日：2003-03-13
申请人： Michihiro Jinnai
发明人： Michihiro Jinnai
IPC分类号： G06K9/62 , G10L15/00 , G10L17/00
CPC分类号： G10L17/08 , G06K9/64 , G10L15/10
摘要： Disclosed is a method for obtaining an accurate detected value of a similarity between images or the like. Original standard and input pattern matrices, each having a feature quantity of an image as an element, are created (Sb1 and Sb3). A weighting vector having a value of a change rate of a kurtosis of a reference pattern vector composed of a reference shape as an element is created, and an original and weighted standard pattern matrix is calculated by a product-sum operation of an element value of the weighting vector and an element value of the original standard pattern matrix (Sb2). Then, an original and weighted input pattern matrix is calculated by a product-sum operation of the element value of the same weighting vector and an element value of the original input pattern matrix (Sb4), and a geometric distance value between the original standard pattern matrix and the original input pattern matrix is calculated as a cosine of an angle between the original and weighted standard pattern matrix and the original and weighted input pattern matrix (Sb5).
摘要翻译：公开了一种用于获得图像等之间的相似度的精确检测值的方法。创建具有作为元素的图像的特征量的原始标准和输入图案矩阵（Sb 1和Sb 3）。创建具有由作为元素的参考形状组成的参考图形向量的峰度的变化率的值的加权矢量，并且通过乘积和运算的元素值的乘积和运算来计算原始和加权的标准模式矩阵加权矢量和原始标准模式矩阵（Sb 2）的元素值。然后，通过相同加权矢量的元素值和原始输入模式矩阵（Sb 4）的元素值的乘积和运算以及原始标准的原始和加权输入模式矩阵之间的几何距离值来计算原始和加权输入模式矩阵模式矩阵和原始输入模式矩阵被计算为原始和加权标准模式矩阵与原始和加权输入模式矩阵（Sb 5）之间的角度的余弦值。

6. 发明授权

US07006970B2 Method for detecting similarity between standard information and input information and method for judging the input information by use of detected result of the similarity 失效
标题翻译：用于检测标准信息和输入信息之间的相似性的方法以及通过使用相似性的检测结果来判断输入信息的方法
公开(公告)号：US07006970B2
公开(公告)日：2006-02-28
申请号：US09951211
申请日：2001-09-11
申请人： Michihiro Jinnai , Hiroshi Yamaguchi
发明人： Michihiro Jinnai , Hiroshi Yamaguchi
IPC分类号： G10L15/08
CPC分类号： G10L15/10 , G06K9/6215
摘要： Disclosed is a method for obtaining a precise detected value of a similarity between voices or the like. Standard and input pattern matrices, each having a voice feature amount as a component, are prepared (S1 and S2). A reference shape having a variance different for each specified component of the pattern matrices is prepared, and positive and negative reference pattern vectors, each having a value of the reference shape as a component, are prepared. Then, while the specified component (a center of the reference shape) being made to move to each component position j1=1 to m1, j2=1 to m2 of the standard pattern matrix, a shape change between the standard and input pattern matrices is substituted for shape changes of the positive and negative reference pattern vectors. And, an amount of change in kurtosis of each reference pattern vector is numerically evaluated to obtain a shape change amount Dj1j2 (S3). Then, a value of a geometric distance between the pattern matrices is calculated from Dj1j2 (S4).
摘要翻译：公开了一种用于获得语音等之间的相似度的精确检测值的方法。准备了具有语音特征量作为分量的标准和输入图形矩阵（S 1和S 2）。准备具有对于图形矩阵的每个指定分量的方差不同的参考形状，并且准备每个具有参考形状的值作为分量的正和负参考图案向量。然后，当指定的分量（参考形状的中心）被移动到每个分量位置j 1 1 1 -1 m 1时，j 2 < / SUB> = 1到m 2，标准图案矩阵和输入图案矩阵之间的形状变化代替正和负参考图案向量的形状变化。并且，对每个参考图案向量的峰度的变化量进行数值估计，以获得形状变化量Dj＆lt; 1＆lt; 2＆gt;（S 3）。然后，从Dj＆gt; 2＆lt; 2＆gt;（S 4）计算图案矩阵之间的几何距离的值。

7. 发明授权

US06170333B2 Apparatus for detecting abnormal sound and method for judging wrong in machine 失效
标题翻译：检测异常声音的装置和机器判断错误的方法
公开(公告)号：US06170333B2
公开(公告)日：2001-01-09
申请号：US09042023
申请日：1998-03-13
申请人： Michihiro Jinnai , Hiroshi Yamaguchi , Yoshinao Ishihara , Jun Ohshima , Fujitaka Taguchi , Masahiro Arakawa , Yoshikazu Kidu
发明人： Michihiro Jinnai , Hiroshi Yamaguchi , Yoshinao Ishihara , Jun Ohshima , Fujitaka Taguchi , Masahiro Arakawa , Yoshikazu Kidu
IPC分类号： G01H1700
CPC分类号： G01H3/00 , F22B37/421
摘要： A standard pattern vector of a normal sound, an input pattern vector of a monitored sound, a positive vector of a reference pattern, and a negative vector of the reference pattern are produced. Regarding each element, the positive vector is increased by an absolute value of a difference between the input pattern vector and the standard pattern vector if the input pattern vector is greater than the standard pattern vector, and the negative vector is increased by the absolute value if the input pattern vector is less than the standard pattern vector. A difference of a kurtosis between the positive vector and the negative vector is calculated, wherein a center of the reference shape is relatively moved to a position of each element of the positive and negative vectors respectively at every calculation. A geometric distance value between the standard pattern vector and the input pattern vector is obtained by calculating a square root of a sum of a square of each kurtosis difference.
摘要翻译：产生正常声音的标准图形矢量，监视声音的输入图形矢量，参考图案的正矢量和参考图案的负矢量。对于每个元素，如果输入图案向量大于标准图案向量，则正向量增加输入图案向量和标准图案向量之间的差的绝对值，并且负向量增加绝对值if 输入图案向量小于标准图案向量。计算正向量和负向量之间的峰度的差异，其中在每次计算时，参考形状的中心分别相对移动到正和负向量的每个元素的位置。通过计算每个峰度差的平方和之和的平方根来获得标准图案矢量与输入图案矢量之间的几何距离值。

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