公开(公告)号：US5704013A

公开(公告)日：1997-12-30

申请号：US365493

申请日：1994-12-28

申请人： Masao Watari ,  Kazuo Ishii ,  Yasuhiko Kato ,  Hiroaki Ogawa ,  Masanori Omote ,  Kazuo Watanabe ,  Katsuki Minamino

发明人： Masao Watari ,  Kazuo Ishii ,  Yasuhiko Kato ,  Hiroaki Ogawa ,  Masanori Omote ,  Kazuo Watanabe ,  Katsuki Minamino

IPC分类号： G06N3/08 ,  G06F15/18

CPC分类号： G06K9/6248 ,  G06N3/08

摘要： A map determination method and apparatus for calculating the coefficients to give a minimum evaluation function quickly and reliably where a map is expressed as the linear sum of a function g.sub.i (X) and a coefficient c.sub.i while a map for transforming a N-dimensional vector (x.sub.0, x.sub.1, x.sub.2, x.sub.3) to a M-dimensional vector y is being decided. The coefficient ci for the map is obtained by giving a learning sample and a teaching sample, obtaining an evaluation function and solving a simultaneous linear equation for which the partial differential is zero.

摘要翻译： 一种映射确定方法和装置，用于在将映射表示为函数gi（X）和系数ci的线性和的同时快速可靠地计算最小评估函数的系数，而用于变换N维向量的映射（ x0，x1，x2，x3）到M维矢量y。 通过给出学习样本和教学样本，获得评估函数并求解偏微分为零的同时线性方程式来获得地图的系数ci。

公开(公告)号：US5764853A

公开(公告)日：1998-06-09

申请号：US548278

申请日：1995-10-25

申请人： Masao Watari ,  Kazuo Ishii ,  Yasuhiko Kato ,  Hiroaki Ogawa ,  Masanori Omote ,  Kazuo Watanabe ,  Katsuki Minamino

发明人： Masao Watari ,  Kazuo Ishii ,  Yasuhiko Kato ,  Hiroaki Ogawa ,  Masanori Omote ,  Kazuo Watanabe ,  Katsuki Minamino

IPC分类号： G10L15/06 ,  G10L15/02 ,  G10L15/14 ,  G10L15/20 ,  G10L19/00 ,  G10L5/06 ,  G10L9/00 ,  G06E1/00 ,  G06E3/00

CPC分类号： G10L15/02 ,  G10L15/20

摘要： A voice recognition device according to the present invention including a voice analyzer for acoustically analyzing voice every predetermined frame unit to extract a feature vector X, a converter for subjecting the feature vector X output from the analyzer to a predetermined conversion process, and a voice recognizer for recognizing the voice on the basis of a new feature vector output from the converter, wherein the converter conducts the predetermined conversion processing according to a mapping F from an N-dimensional vector space .OMEGA..sub.N to an M-dimensional vector space .OMEGA..sub.M, the feature vector X is a vector on the N-dimensional vector space .OMEGA..sub.N and the function f.sub.m (X) of an m-th component of the mapping F is represented by the following linear summation of the products of functions g.sub.m.sup.k (X) and coefficients c.sub.m.sup.k of L.sub.m : ##EQU1## Each function g.sub.m.sup.k (X) may be set to a monomial.

摘要翻译： 根据本发明的语音识别装置包括：语音分析器，用于每个预定帧单元声音分析语音以提取特征向量X;转换器，用于使从分析器输出的特征矢量X经历预定的转换处理;以及语音识别器 用于基于从转换器输出的新特征向量来识别语音，其中，转换器根据从N维向量空间OMEGA N到M维向量空间OMEGA M的映射F进行预定的转换处理， 特征向量X是N维向量空间OMEGA N上的向量，映射F的第m个分量的函数fm（X）由函数gmk（X）和系数的乘积的以下线性求和来表示 cmk的Lm：每个函数gmk（X）可以被设置为一个单项。

公开(公告)号：US06055536A

公开(公告)日：2000-04-25

申请号：US868443

申请日：1997-06-03

申请人： Masato Shimakawa ,  Makoto Akabane ,  Bao Hongchang ,  Junichi Rekimoto ,  Hiroaki Kitano ,  Kazunori Sasano ,  Kazuo Ishii ,  Keiichi Yamada ,  Hiroaki Ogawa ,  Hiroshi Kakuda ,  Yasuharu Asano ,  Hitoshi Honda ,  Satoshi Fujimura ,  Atsuo Hiroe

发明人： Masato Shimakawa ,  Makoto Akabane ,  Bao Hongchang ,  Junichi Rekimoto ,  Hiroaki Kitano ,  Kazunori Sasano ,  Kazuo Ishii ,  Keiichi Yamada ,  Hiroaki Ogawa ,  Hiroshi Kakuda ,  Yasuharu Asano ,  Hitoshi Honda ,  Satoshi Fujimura ,  Atsuo Hiroe

IPC分类号： G06F12/00 ,  G06F13/00 ,  G06F17/30 ,  G06Q30/02 ,  G06Q30/06 ,  G06Q50/00 ,  G06Q50/10 ,  G10L15/26

CPC分类号： G06F17/30864 ,  G10L15/26 ,  Y10S707/99942 ,  Y10S707/99943

摘要： An information processing system stores information of various types, which is obtained in the real world, in connection with keys indicative of the attribute and feature of the information so that the real-world information is stored quickly and surely in the virtual world which is formed of the linkage of information and stored information of various types is retrieved easily.

摘要翻译： 信息处理系统结合指示信息的属性和特征的键来存储在现实世界中获得的各种类型的信息，使得真实世界信息被快速且可靠地存储在形成的虚拟世界中 信息的链接和各种类型的存储信息被容易地检索。

公开(公告)号：US07013277B2

公开(公告)日：2006-03-14

申请号：US09794887

申请日：2001-02-26

申请人： Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa ,  Helmut Lucke

发明人： Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa ,  Helmut Lucke

IPC分类号： G10L15/00

CPC分类号： G10L15/193 ,  G10L2015/085

摘要： A preliminary word-selecting section selects one or more words following words which have been obtained in a word string serving as a candidate for a result of speech recognition; and a matching section calculates acoustic or linguistic scores for the selected words, and forms a word string serving as a candidate for a result of speech recognition according to the scores. A control section generates word-connection relationships between words in the word string serving as a candidate for a result of speech recognition, sends them to a word-connection-information storage section, and stores them in it. A re-evaluation section corrects the word-connection relationships stored in the word-connection-information storage section 16, and the control section determines a word string serving as the result of speech recognition according to the corrected word-connection relationships.

摘要翻译： 初步字选择部选择在用作语音识别结果的候选者的字串中获得的一个或多个单词， 并且匹配部分计算所选择的单词的声学或语言得分，并且根据分数形成用作语音识别结果的候选的词串。 控制部分生成用作语音识别结果候选的字串中的字之间的字连接关系，将它们发送到字连接信息存储部分，并将它们存储在其中。 重新评估部分校正存储在字连接信息存储部分16中的字连接关系，并且控制部分根据校正的字连接关系确定用作语音识别结果的字串。

公开(公告)号：US07249017B2

公开(公告)日：2007-07-24

申请号：US10785246

申请日：2004-02-24

申请人： Helmut Lucke ,  Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa

发明人： Helmut Lucke ,  Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa

IPC分类号： G10L15/08 ,  G06F17/27

CPC分类号： G10L15/187 ,  G10L2015/025

摘要： In order to prevent degradation of speech recognition accuracy due to an unknown word, a dictionary database has stored therein a word dictionary in which are stored, in addition to words for the objects of speech recognition, suffixes, which are sound elements and a sound element sequence, which form the unknown word, for classifying the unknown word by the part of speech thereof. Based on such a word dictionary, a matching section connects the acoustic models of an sound model database, and calculates the score using the series of features output by a feature extraction section on the basis of the connected acoustic model. Then, the matching section selects a series of the words, which represents the speech recognition result, on the basis of the score.

摘要翻译： 为了防止由于未知词引起的语音识别精度的降低，字典数据库中存储有词语词典，除了用于语音识别的对象的词之外，还存储有作为声音元素和声音元素的后缀的词典 序列，其形成未知单词，用于通过其部分语音对未知单词进行分类。 基于这样的词典，匹配部分连接声音模型数据库的声学模型，并且使用基于连接的声学模型的特征提取部分输出的一系列特征来计算分数。 然后，匹配部分基于分数来选择表示语音识别结果的一系列单词。

公开(公告)号：US06961701B2

公开(公告)日：2005-11-01

申请号：US09798521

申请日：2001-03-03

申请人： Hiroaki Ogawa ,  Katsuki Minamino ,  Yasuharu Asano ,  Helmut Lucke

发明人： Hiroaki Ogawa ,  Katsuki Minamino ,  Yasuharu Asano ,  Helmut Lucke

IPC分类号： G10L15/18 ,  G10L15/02 ,  G10L17/00 ,  G10L15/08

CPC分类号： G10L17/02 ,  G10L17/16 ,  G10L2015/025

摘要： An extended-word selecting section calculates a score for a phoneme string formed of one more phonemes, corresponding to a user's speech, and searches a large-vocabulary-dictionary for a word having one or more phonemes equal to or similar to those of a phoneme string having a score equal to or higher than a predetermined value. A matching section calculates scores for the word searched for by the extended-word selecting section in addition to a word preliminary word-selecting section. A control section determines a word string as the result of recognition of the speech uttered by the user.

摘要翻译： 扩展字选择部分计算由与用户的语音相对应的一个以上音素形成的音素串的分数，并且搜索具有等于或类似于音素的一个或多个音素的单词的大词汇词典 具有等于​​或高于预定值的分数的字符串。 匹配部分除了字初步字选择部分之外，还计算由扩展字选择部分搜索的字的分数。 控制部分确定作为用户发出的语音的识别结果的字串。

公开(公告)号：US20050075877A1

公开(公告)日：2005-04-07

申请号：US10416092

申请日：2001-11-07

申请人： Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa ,  Helmut Lucke

发明人： Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa ,  Helmut Lucke

IPC分类号： G10L15/18 ,  G10L15/08 ,  G10L15/10 ,  G10L15/14 ,  G10L15/00

CPC分类号： G10L15/08 ,  G10L15/083

摘要： A speech recognizing device for efficient processing while keeping a high speech recognizing performance. A matching unit (14) computes the score of a word preliminarily selected by a word preliminary selection unit (13) and determines candidates of the speech recognition result on the basis of the score. A control unit (11) creates a word connection relation between the words of a word sequence, which is a candidate of the speech recognition result and stores them in a word connection information storage unit (16). A revaluation unit (15) corrects the word connection relation serially, and the control unit ( 11) defines the speech recognition result on the basis of the word connection relation corrected. A word connection relation managing unit (21) limits the time corresponding to the boundary of a word expressed by the word connection relation, and a word connection relation managing unit (22) limits the starting time of the word preliminarily selected by the word preliminary selection unit (13). The speech recognizing device can be applied to an interactive system which responds to the speech recognition result.

摘要翻译： 一种用于在保持高语音识别性能的同时高效处理的语音识别装置。 匹配单元（14）计算由词初步选择单元（13）预先选择的单词的分数，并根据得分确定语音识别结果的候选。 控制单元（11）创建作为语音识别结果的候选者的字序列的字之间的字连接关系，并将它们存储在字连接信息存储单元（16）中。 重估单元（15）串行地校正字连接关系，并且控制单元（11）基于校正的字连接关系来定义语音识别结果。 字连接关系管理单元（21）限制与字连接关系所表示的字的边界对应的时间，并且字连接关系管理单元（22）限制由初始选择预先选择的单词的开始时间 单位（13）。 语音识别装置可以应用于响应于语音识别结果的交互式系统。

公开(公告)号：US07881935B2

公开(公告)日：2011-02-01

申请号：US10019125

申请日：2001-02-16

申请人： Yasuharu Asano ,  Katsuki Minamino ,  Hiroaki Ogawa ,  Helmut Lucke

发明人： Yasuharu Asano ,  Katsuki Minamino ,  Hiroaki Ogawa ,  Helmut Lucke

IPC分类号： G10L15/04 ,  G10L15/14

CPC分类号： G10L15/08 ,  G10L15/18 ,  G10L2015/085

摘要： A speech recognition apparatus in which the accuracy in speech recognition is improved as the resource is prevented from increasing. Such a word which is probable as the result of the speech recognition is selected on the basis of an acoustic score and a linguistic score, while word selection is also performed on the basis of a measure different from the acoustic score, such as the number of phonemes being small, a part of speech being a pre-set one, inclusion in the past results of speech recognition or the linguistic score being not less than a pre-set value. The words so selected are subjected to matching processing.

摘要翻译： 一种在防止资源增加时语音识别精度提高的语音识别装置。 基于声学得分和语言得分来选择可能作为语音识别结果的这样一个词，而基于与声分数不同的度量来执行词选择，例如， 音素很小，部分言语是预先设定的，包括过去的语音识别结果或语言分数不低于预设值。 所选择的单词将进行匹配处理。

公开(公告)号：US07240002B2

公开(公告)日：2007-07-03

申请号：US10416092

申请日：2001-11-07

申请人： Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa ,  Helmut Lucke

发明人： Katsuki Minamino ,  Yasuharu Asano ,  Hiroaki Ogawa ,  Helmut Lucke

IPC分类号： G10L15/04

CPC分类号： G10L15/08 ,  G10L15/083

摘要： The present invention provides a speech recognition apparatus having high speech recognition performance and capable of performing speech recognition in a highly efficient manner. A matching unit 14 calculates the scores of words selected by a preliminary word selector 13 and determines a candidate for a speech recognition result on the basis of the calculated scores. A control unit 11 produces word connection relationships among words included in a word series employed as a candidate for the speech recognition result and stores them into a word connection information storage unit 16. A reevaluation unit 15 corrects the word connection relationships one by one. On the basis of the corrected word connection relationships, the control unit 11 determines the speech recognition result. A word connection managing unit 21 limits times allowed for a boundary between words represented by the word connection relationships to be located thereat. A word connection managing unit 22 limits start times of words preliminarily selected by the preliminary word selector 13. The present invention can be applied to an interactive system that recognizes an input speech and responds to the speech recognition result.

摘要翻译： 本发明提供了具有高语音识别性能并且能够以高效的方式执行语音识别的语音识别装置。 匹配单元14计算由初步词选择器13选择的单词的分数，并且基于所计算的分数来确定语音识别结果的候选。 控制单元11产生用作语音识别结果候选的单词序列中包含的单词之间的字连接关系，并将它们存储到单词连接信息存储单元16中。 重新评估单元15逐个地修正单词连接关系。 基于校正后的字连接关系，控制单元11确定语音识别结果。 字连接管理单元21限制由字连接关系所表示的字之间的边界所允许的时间。 字连接管理单元22限制由初步词选择器13预先选择的单词的开始时间。 本发明可以应用于识别输入语音并响应于语音识别结果的交互式系统。

公开(公告)号：US20110029311A1

公开(公告)日：2011-02-03

申请号：US12817526

申请日：2010-06-17

申请人： Katsuki MINAMINO ,  Hitoshi Honda ,  Yoshinori Maeda ,  Hiroaki Ogawa

发明人： Katsuki MINAMINO ,  Hitoshi Honda ,  Yoshinori Maeda ,  Hiroaki Ogawa

IPC分类号： G10L15/04 ,  G10L15/06

CPC分类号： G10L15/183

摘要： There is provided a voice processing device. The device includes: score calculation unit configured to calculate a score indicating compatibility of a voice signal input on the basis of an utterance of a user with each of plural pieces of intention information indicating each of a plurality of intentions; intention selection unit configured to select the intention information indicating the intention of the utterance of the user among the plural pieces of intention information on the basis of the score calculated by the score calculation unit; and intention reliability calculation unit configured to calculate the reliability with respect to the intention information selected by the intention selection unit on the basis of the score calculated by the score calculation unit.

摘要翻译： 提供语音处理装置。 该设备包括：分数计算单元，被配置为计算表示基于用户的话语输入的语音信号的兼容性的分数与指示多个意图中的每一个的多个意图信息中的每一个; 意图选择单元，被配置为基于由分数计算单元计算的得分，在多个意图信息中选择表示用户的发音意图的意图信息; 以及意图可靠性计算单元，被配置为基于由分数计算单元计算出的分数来计算与意图选择单元选择的意图信息相关的可靠性。