专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US4670850A Pattern matching apparatus 失效
标题翻译：模式匹配装置
公开(公告)号：US4670850A
公开(公告)日：1987-06-02
申请号：US631692
申请日：1984-07-17
申请人： Hiroaki Sakoe
发明人： Hiroaki Sakoe
IPC分类号： G06K9/62 , G06T7/00 , G10L11/00 , G10L15/00 , G10L15/12 , G10L5/00
CPC分类号： G10L15/12 , G10L15/00
摘要： For improved pattern recognition, the reference pattern feature sequence contains control parameters (operators) which provide branching and/or omission of those portions of words which may be non-standard due to speaker or dialect deformations. A pattern matching apparatus comprising a stack controller with two PUSH/POP stacks for addressing reference patterns to be used for correlations against the detected pattern information. The reference patterns may contain control characters indicating alternative reference pattern segments or segments which may be omitted.
摘要翻译：为了改进模式识别，参考模式特征序列包含控制参数（运算符），它们由于说话者或方言变形而提供分支和/或省略那些可能是非标准的单词部分。一种模式匹配装置，包括具有两个PUSH / POP堆栈的堆栈控制器，用于寻址要用于与检测到的模式信息相关的参考模式。参考图案可以包含指示可以省略的替代参考图案片段或片段的控制字符。

22. 发明授权

US4513435A System operable as an automaton for recognizing continuously spoken words with reference to demi-word pair reference patterns 失效
标题翻译：可用作自动机的系统，用于识别连续口头词，参考二字对对参考模式
公开(公告)号：US4513435A
公开(公告)日：1985-04-23
申请号：US370637
申请日：1982-04-21
申请人： Hiroaki Sakoe , Seibi Chiba
发明人： Hiroaki Sakoe , Seibi Chiba
IPC分类号： G10L11/00 , G10L15/00 , G10L15/10 , G10L1/00
CPC分类号： G10L15/00
摘要： A system for recognizing a continuously spoken word sequence with reference to preselected reference words with the problem of coarticulation removed, comprises a pattern memory for memorizing demi-word pair reference patterns consisting of a former and a latter reference pattern segment for each reference word and a word pair reference pattern segment for each permutation with repetition of two words selected from the preselected reference words. A recognition unit is operable as a finite-state automaton on concatenating the demi-word pair reference patterns so that no contradiction occurs at each interface of the reference patterns in every concatenation. It is possible to use the automaton in restricting the number of reference patterns in each concatenation either to an odd or an even positive integer.
摘要翻译：一种用于识别连续口语单词序列的系统，涉及去除了coarticulation问题的预先选择的参考词，包括用于存储由每个参考单词的前一个和后一个参考图形段组成的单词对参考模式的模式存储器，以及用于每次排列的字对参考图案片段，其中重复从预选参考词中选择的两个词。一个识别单元可以作为有限状态自动机来连接这个二字对对参考图案，使得在每个级联中的参考图形的每个界面处不发生矛盾。可以使用自动机将每个级联中的参考模式的数量限制为奇数或偶数正整数。

23. 发明授权

US4282403A Pattern recognition with a warping function decided for each reference pattern by the use of feature vector components of a few channels 失效
标题翻译：通过使用几个通道的特征向量分量，对每个参考模式决定了具有翘曲函数的模式识别
公开(公告)号：US4282403A
公开(公告)日：1981-08-04
申请号：US64965
申请日：1979-08-08
申请人： Hiroaki Sakoe
发明人： Hiroaki Sakoe
IPC分类号： G10L11/00 , G06K9/62 , G06K9/64 , G06T1/00 , G10L15/00 , G10L15/12 , G10L1/00
CPC分类号： G10L15/12 , G06K9/6206 , G10L15/00
摘要： In a pattern recognition device according to pattern matching, one or more specific dimensions of vector components are memorized for each reference pattern feature vector sequence in a reference pattern memory for the reference pattern feature vector sequences. A warping function for time-normalizing input pattern feature vectors of a sequence and the vectors of each reference pattern feature vector sequence is determined so as to minimize the difference between a pattern represented by the specific vector components of the specific dimension or dimensions and another pattern represented by the vector components corresponding in the input pattern feature vector sequence to the specific reference pattern feature vector components as regards the dimensions of a space in which each input or reference pattern feature vector is defined. The input pattern feature vector sequence and each reference pattern feature vector sequence are subjected to nonlinear pattern matching with reference to the warping function. The pattern matching may be between the vector components of all dimensions or those of several dimensions including the specific dimension or dimensions. Preferably, one or more dimensions are specified as the specific one or ones by selecting each dimension for which a variation with time of a pattern represented by the reference pattern feature vector components is a maximum of similar variations of patterns represented by the vector components of other dimensions.
摘要翻译：在根据图案匹配的图案识别装置中，针对参考图案特征向量序列的参考图案存储器中的每个参考图案特征向量序列存储矢量分量的一个或多个特定维度。确定用于对序列的输入模式特征向量进行时间归一化和每个参考模式特征向量序列的向量的变形函数，以使由特定维度或维度的特定向量分量表示的模式与另一模式之间的差异最小化由输入图形特征向量序列中对应的矢量分量表示为与定义每个输入或参考图案特征向量的空间的尺寸相对于特定参考图案特征向量分量。输入图形特征向量序列和每个参考图形特征向量序列参照扭曲函数进行非线性模式匹配。图案匹配可以在所有尺寸的矢量分量或包括特定尺寸或尺寸的几个维度的矢量分量之间。优选地，一个或多个维度被指定为特定的一个或多个维度，通过选择其中由参考图案特征向量分量表示的图案随时间变化的变化是由其他的矢量分量表示的图案的相似变化的最大值尺寸。

24. 发明授权

US4256924A Device for recognizing an input pattern with approximate patterns used for reference patterns on mapping 失效
标题翻译：用于在映射时识别用于参考模式的近似模式的输入模式的装置
公开(公告)号：US4256924A
公开(公告)日：1981-03-17
申请号：US095263
申请日：1979-11-19
申请人： Hiroaki Sakoe
发明人： Hiroaki Sakoe
IPC分类号： G10L11/00 , G06K9/62 , G10L15/00 , G10L15/12 , G10L1/00
CPC分类号： G10L15/12 , G10L15/00
摘要： In a speech recognition system which time-normalizes (i.e. aligns by time-warping) each pre-stored reference pattern of feature vectors b.sub.j before comparison with the input signal pattern vectors a.sub.i, an improved time-alignment technique requiring less calculation, by selecting "standard" vectors v.sub.m(j) which approximate the reference vectors thereby simplifying the derivation of the time-warp mapping function j=j(i).
摘要翻译：在与输入信号图案矢量ai进行比较之前，对特征矢量bj进行时间归一化（即，通过时间扭曲对齐）的每个预先存储的参考图案的语音识别系统中，通过选择“ 标准“向量vm（j），从而简化了时间扭曲映射函数j = j（i）的推导。

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