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

US4736429A Apparatus for speech recognition 失效
标题翻译：语音识别装置
公开(公告)号：US4736429A
公开(公告)日：1988-04-05
申请号：US618368
申请日：1984-06-07
申请人： Katsuyuki Niyada , Ikuo Inoue , Satoru Fujii , Shuji Morii
发明人： Katsuyuki Niyada , Ikuo Inoue , Satoru Fujii , Shuji Morii
IPC分类号： G10L15/10 , G10L15/04 , G10L5/00
CPC分类号： G10L15/04
摘要： Apparatus for speech recognition, having each phoneme as a fundamental recognition unit, recognizes input speech by discriminating phonemes in the input speech. The apparatus comprises a memory for storing phoneme standard patterns of phonemes or phoneme groups; a spectrum analyzer for obtaining parameters indicative of the input speech signal spectrum; a statistical distance measure similarity calculator calculates the degree of similarity between the output of the spectrum analyzer and standard patterns stored in the memory; a segmentation portion for segmenting by using time-dependent low- and high-frequency power variations of the input speech signal and results from the similarity calculator; and a phoneme discriminator for recognizing phonemes by using the results from the similarity calculator.
摘要翻译：具有每个音素作为基本识别单元的语音识别装置通过在输入语音中区分音素来识别输入语音。该装置包括用于存储音素或音素组的音素标准模式的存储器; 频谱分析器，用于获得指示输入语音信号频谱的参数; 统计距离测量相似度计算器计算频谱分析仪的输出与存储在存储器中的标准模式之间的相似度; 分割部分，用于通过使用输入语音信号的时间相关的低频和高频功率变化和来自相似性计算器的结果来分割; 以及通过使用相似度计算器的结果来识别音素的音素鉴别器。

2. 发明授权

US4885791A Apparatus for speech recognition 失效
标题翻译：语音识别装置
公开(公告)号：US4885791A
公开(公告)日：1989-12-05
申请号：US920785
申请日：1986-10-20
申请人： Satoru Fujii , Katsuyuki Niyada , Shuji Morii , Taisuke Watanabe
发明人： Satoru Fujii , Katsuyuki Niyada , Shuji Morii , Taisuke Watanabe
IPC分类号： G10L15/00
CPC分类号： G10L15/00
摘要： Disclosed is a speech recognition apparatus comprising: a speech analysis portion for extracting parameters necessary for determination of spoken words; a speech period detecting portion for extracting one or more combinations of speech periods using the parameters; and a structure analysis portion for detecting feature points indicative of phoneme structure of each word and for determining a word through computation of similarity to proposed words in accordance with the presence and absence of the feature points. Therefore, erroneous recognition due to noise introduction or the like can be reduced by detecting one or more combinations of proposed speech periods by the speech period detecting portion. By extracting only necessary number of extracting points, which contribute to the distinguishment between words, with reference to analysis procedure provided for each word, the sharpness of determination is bettered. More stable operation than conventional apparatus has been achieved in connection with time base expansion/compression. Small numbers of parameters obtained through speech analysis are used to reduce the amount of computation, while the above-mentioned parameters are stable against difference in phenemes due to difference in speakers.
摘要翻译：公开了一种语音识别装置，包括：语音分析部分，用于提取确定口语所需的参数; 语音周期检测部分，用于使用参数提取语音周期的一个或多个组合; 以及结构分析部分，用于检测指示每个单词的音素结构的特征点，并且根据特征点的存在和不存在，通过计算与所提出的单词的相似度来确定单词。因此，可以通过由语音周期检测部分检测所提出的语音周期的一个或多个组合来减少由噪声引入引起的错误识别等。通过提取必要数量的提取点，这有助于区分词，参考为每个单词提供的分析程序，提高了确定的清晰度。结合时基扩展/压缩已经实现了比传统装置更稳定的操作。使用通过语音分析获得的少量参数来减少计算量，而上述参数由于扬声器的差异而对于差异性是稳定的。

3. 发明授权

US5131043A Method of and apparatus for speech recognition wherein decisions are made based on phonemes 失效
标题翻译：用于语音识别的方法和装置，其中基于音素进行决定
公开(公告)号：US5131043A
公开(公告)日：1992-07-14
申请号：US441225
申请日：1989-11-20
申请人： Satoru Fujii , Katsuyuki Niyada
发明人： Satoru Fujii , Katsuyuki Niyada
IPC分类号： G10L15/00
CPC分类号： G10L15/10
摘要： Linear prediction coefficients of a speech signal including unknown words are derived for each of successive periodic frame intervals. For every frame over the duration of an individual phoneme of the speech signal, the degree of similarity of stored coefficients of known words and derived coefficients of the unknown words are calculated so that at the end of the individual phonemes, the degree of similarity is calculated. Phoneme segmentation data are derived in response to the speech signal and combined with the calculated degree of similarity over the individual phoneme to derive phoneme strings of the speech signal. The derived and stored phoneme strings are compared to indicate the words stored in a word dictionary having the greatest similarity with the derived phoneme strings.
摘要翻译：对于每个连续的周期性帧间隔导出包括未知字的语音信号的线性预测系数。对于在语音信号的单个音素的持续时间内的每个帧，计算已知单词的存储系数和未知单词的导出系数的相似度，使得在单个音素的末尾，计算相似度。音素分割数据是响应于语音信号导出的，并且与计算的各个音素上的相似程度相结合以导出语音信号的音素串。将导出和存储的音素字符串进行比较，以指示与导出的音素串具有最大相似性的词典中存储的词。

4. 发明授权

US4991216A Method for speech recognition 失效
标题翻译：语音识别方法
公开(公告)号：US4991216A
公开(公告)日：1991-02-05
申请号：US501386
申请日：1990-03-23
申请人： Satoru Fujii , Katsuyuki Niyada
发明人： Satoru Fujii , Katsuyuki Niyada
IPC分类号： G10L15/00
CPC分类号： G10L15/10
摘要： Phoneme standard patterns are prepared beforehand using speech sounds from a number of individual speakers. Unknown input speech sounds are divided into continuous frames and then some of these frames are extracted such that extracted frames include noncontinuous frames. LPC cepstrum coefficients are obtained for each of the frames and a mean value is obtained from the LPC cepstrum coefficients for each of the phonemes. A first standard pattern is then formed for each of the phonemes belonging to each group determined by characteristics of known speech sounds. Spectrum information of the unknown input speech sounds is produced using such extracted frames, and is then compared with the phoneme standard patterns prestored in a storage to determine and recognize phonemes of the unknown speech sounds by calculating similarity between the two using a statistical distance measure. When obtaining LPC cepstrum coefficients through LPC analysis, the order of LPC cepstrum coefficients is set to a value below the order of LPC analysis. The method according to the present invention reduces the amount of calculations necessary to perform speech recognition without deteriorating phoneme and word recognition rate.
摘要翻译：预先使用来自多个扬声器的讲话声音准备音素标准图案。未知的输入语音被分为连续帧，然后提取这些帧中的一些，使得提取的帧包括非连续帧。对于每个帧获得LPC倒谱系数，并且从每个音素的LPC倒频谱系数获得平均值。然后，通过已知语音的特征确定属于每个组的每个音素，形成第一标准模式。使用这种提取的帧产生未知输入语音的频谱信息，然后将其与预先存储在存储器中的音素标准模式进行比较，以通过使用统计距离测量来计算两者之间的相似度来确定和识别未知语音的音素。通过LPC分析获得LPC倒谱系数时，LPC倒谱系数的顺序设置为低于LPC分析顺序的值。根据本发明的方法减少了在不恶化音素和字识别率的情况下执行语音识别所需的计算量。

5. 发明授权

US09252189B2 Nonvolatile semiconductor memory element, nonvolatile semiconductor memory device, and method for manufacturing nonvolatile semiconductor memory device 有权
标题翻译：非易失性半导体存储元件，非易失性半导体存储器件以及用于制造非易失性半导体存储器件的方法
公开(公告)号：US09252189B2
公开(公告)日：2016-02-02
申请号：US13996203
申请日：2012-06-18
申请人： Satoru Fujii , Kiyotaka Tsuji , Takumi Mikawa
发明人： Satoru Fujii , Kiyotaka Tsuji , Takumi Mikawa
IPC分类号： H01L27/24 , H01L45/00 , H01L29/66 , H01L29/872 , H01L27/22
CPC分类号： H01L27/2409 , H01L27/228 , H01L27/2436 , H01L27/2463 , H01L29/66143 , H01L29/872 , H01L45/04 , H01L45/06 , H01L45/1233 , H01L45/145 , H01L45/146 , H01L45/16 , H01L45/1608 , H01L45/1616 , H01L45/1625 , H01L45/1675
摘要： A nonvolatile semiconductor memory element includes: a variable resistance element including a first electrode, a variable resistance layer, and a second electrode, and having a resistance value which changes according to a polarity of an electric pulse applied between the first electrode and the second electrode; and a current steering element which is electrically connected to the variable resistance element, allows a current to flow bidirectionally, and has a nonlinear current-voltage characteristic. The current steering element (i) has a structure in which a first current steering element electrode, a first current steering layer, and a second current steering element electrode are stacked in this order, and (ii) includes a second current steering layer which covers side surfaces of the first current steering element electrode, the first current steering layer, and the second current steering element electrode.
摘要翻译：非易失性半导体存储元件包括：可变电阻元件，包括第一电极，可变电阻层和第二电极，并且具有根据施加在第一电极和第二电极之间的电脉冲的极性而变化的电阻值 ; 并且电连接到可变电阻元件的电流导向元件允许电流双向流动，并且具有非线性电流 - 电压特性。当前的操舵元件（i）具有第一电流导向元件电极，第一电流导向层和第二电流操舵元件电极按此顺序堆叠的结构，（ⅱ）包括覆盖第一电流操舵元件电极，第一电流导向层和第二电流导向元件电极的侧面。

6. 发明申请

US20130270510A1 NONVOLATILE SEMICONDUCTOR MEMORY ELEMENT, NONVOLATILE SEMICONDUCTOR MEMORY DEVICE, AND METHOD FOR MANUFACTURING NONVOLATILE SEMICONDUCTOR MEMORY DEVICE 有权
标题翻译：非易失性半导体存储器元件，非易失性半导体存储器件及其制造非易失性半导体存储器件的方法
公开(公告)号：US20130270510A1
公开(公告)日：2013-10-17
申请号：US13996203
申请日：2012-06-18
申请人： Satoru Fujii , Kiyotaka Tsuji , Takumi Mikawa
发明人： Satoru Fujii , Kiyotaka Tsuji , Takumi Mikawa
IPC分类号： H01L27/24 , H01L45/00
CPC分类号： H01L27/2409 , H01L27/228 , H01L27/2436 , H01L27/2463 , H01L29/66143 , H01L29/872 , H01L45/04 , H01L45/06 , H01L45/1233 , H01L45/145 , H01L45/146 , H01L45/16 , H01L45/1608 , H01L45/1616 , H01L45/1625 , H01L45/1675
摘要： A nonvolatile semiconductor memory element includes: a variable resistance element including a first electrode, a variable resistance layer, and a second electrode, and having a resistance value which changes according to a polarity of an electric pulse applied between the first electrode and the second electrode; and a current steering element which is electrically connected to the variable resistance element, allows a current to flow bidirectionally, and has a nonlinear current-voltage characteristic. The current steering element (i) has a structure in which a first current steering element electrode, a first semiconductor layer, and a second current steering element electrode are stacked in this order, and (ii) includes a second semiconductor layer which covers side surfaces of the first current steering element electrode, the first semiconductor layer, and the second current steering element electrode.
摘要翻译：非易失性半导体存储元件包括：可变电阻元件，包括第一电极，可变电阻层和第二电极，并且具有根据施加在第一电极和第二电极之间的电脉冲的极性而变化的电阻值 ; 并且电连接到可变电阻元件的电流导向元件允许电流双向流动，并且具有非线性电流 - 电压特性。当前的操舵元件（i）具有第一电流操舵元件电极，第一半导体层和第二电流操舵元件电极依次层叠的结构，（ⅱ）包括覆盖侧面的第二半导体层的第一电流操舵元件电极，第一半导体层和第二电流操舵元件电极。

7. 发明申请

US20110294259A1 NONVOLATILE MEMORY ELEMENT, MANUFACTURING METHOD THEREOF, AND NONVOLATILE SEMICONDUCTOR APPARATUS USING THE NONVOLATILE MEMORY ELEMENT 有权
标题翻译：非易失性存储元件，其制造方法和使用非易失性存储元件的非易失性半导体器件
公开(公告)号：US20110294259A1
公开(公告)日：2011-12-01
申请号：US13205408
申请日：2011-08-08
申请人： Yoshihiko KANZAWA , Koji Katayama , Satoru Fujii , Shunsaku Muraoka , Koichi Osano , Satoru Mitani , Ryoko Miyanaga , Takeshi Takagi , Kazuhiko Shimakawa
发明人： Yoshihiko KANZAWA , Koji Katayama , Satoru Fujii , Shunsaku Muraoka , Koichi Osano , Satoru Mitani , Ryoko Miyanaga , Takeshi Takagi , Kazuhiko Shimakawa
IPC分类号： H01L21/36
CPC分类号： H01L27/101 , G11C13/0007 , G11C13/004 , G11C13/0069 , G11C2013/0073 , G11C2213/32 , G11C2213/71 , G11C2213/72 , G11C2213/79 , H01L27/2409 , H01L27/2436 , H01L27/2481 , H01L45/08 , H01L45/1233 , H01L45/146 , H01L45/1625 , H01L45/1675 , Y10S438/90
摘要： A nonvolatile memory element comprises a first electrode layer (103), a second electrode (107), and a resistance variable layer (106) which is disposed between the first electrode layer (103) and the second electrode layer (107), a resistance value of the resistance variable layer varying reversibly according to electric signals having different polarities which are applied between the electrodes (103), (107), wherein the resistance variable layer (106) has a first region comprising a first oxygen-deficient tantalum oxide having a composition represented by TaOx (0
摘要翻译：非易失性存储元件包括设置在第一电极层（103）和第二电极层（107）之间的第一电极层（103），第二电极（107）和电阻变化层（106），电阻电阻变化层的值根据施加在电极（103），（107）之间的具有不同极性的电信号而可逆地变化，其中电阻变化层（106）具有第一区域，该第一区域包括第一氧缺陷型氧化钽，由TaOx（0

8. 发明申请

US20100148143A1 NONVOLATILE MEMORY ELEMENT, MANUFACTURING METHOD THEREOF, AND NONVOLATILE SEMICONDUCTOR APPARATUS USING NONVOLATILE MEMORY ELEMENT 有权
标题翻译：非易失性存储元件，其制造方法和非易失性存储器元件的非线性半导体器件
公开(公告)号：US20100148143A1
公开(公告)日：2010-06-17
申请号：US12600793
申请日：2008-05-16
申请人： Satoru Fujii , Yoshihiko Kanzawa , Takeshi Takagi , Kazuhiko Shimakawa
发明人： Satoru Fujii , Yoshihiko Kanzawa , Takeshi Takagi , Kazuhiko Shimakawa
IPC分类号： H01L45/00 , H01L21/16
CPC分类号： H01L27/101 , H01L27/2409 , H01L27/2418 , H01L27/2436 , H01L27/2481 , H01L45/04 , H01L45/1233 , H01L45/145 , H01L45/1625
摘要： A nonvolatile semiconductor apparatus of the present invention comprises (103), a second electrode (105), and a resistance variable layer (104) disposed between the first electrode (103) and the second electrode (105), a resistance value of the resistance variable layer being switchable reversibly in response to an electric signal applied between the electrodes (103), (105), wherein the resistance variable layer (104) comprises an oxide containing tantalum and nitrogen.
摘要翻译：本发明的非易失性半导体装置包括：（103），设置在第一电极（103）和第二电极（105）之间的第二电极（105）和电阻变化层（104），电阻值可变层可响应施加在电极（103），（105）之间的电信号而可逆地切换，其中电阻变化层（104）包括含有钽和氮的氧化物。

9. 发明申请

US20090321709A1 MEMORY ELEMENT, MEMORY APPARATUS, AND SEMICONDUCTOR INTEGRATED CIRCUIT 有权
标题翻译：存储元件，存储器和半导体集成电路
公开(公告)号：US20090321709A1
公开(公告)日：2009-12-31
申请号：US12376256
申请日：2007-08-17
申请人： Shunsaku Muraoka , Satoru Fujii , Satoru Mitani , Koichi Osano
发明人： Shunsaku Muraoka , Satoru Fujii , Satoru Mitani , Koichi Osano
IPC分类号： H01L27/10 , H01L45/00 , H01L49/00
CPC分类号： G11C13/0007 , G11C11/5685 , G11C2213/31 , G11C2213/32 , G11C2213/55 , G11C2213/79 , H01L27/101 , H01L27/2436 , H01L27/2463 , H01L45/04 , H01L45/1233 , H01L45/146 , H01L45/147 , H01L45/1625 , H01L45/1683
摘要： A memory element comprises a first electrode, a second electrode, and a resistance variable film 2 which is disposed between the first and second electrodes to be connected to the first and second electrodes, a resistance value of the resistance variable film 2 varying based on voltage applied between the first and second electrodes, the resistance variable film 2 includes a layer 2a made of Fe3O4 and a layer 2b made of Fe2O3 or a spinel structure oxide which is expressed as MFe2O4 (M: metal element except for Fe); and the layer 2a made of Fe3O4 is thicker than the layer 2b made of Fe2O3 or the spinel structure oxide.
摘要翻译：存储元件包括第一电极，第二电极和电阻可变膜2，电阻可变膜2设置在与第一和第二电极连接的第一和第二电极之间，电阻变化膜2的电阻值基于电压变化电阻可变膜2包括由Fe 3 O 4制成的层2a和由Fe 2 O 3制成的层2b或以MFe 2 O 4表示的尖晶石结构氧化物（M：除了Fe之外的金属元素）; 由Fe 3 O 4制成的层2a比由Fe 2 O 3或尖晶石结构氧化物制成的层2b厚。

10. 发明授权

US07035629B2 User interface control method and system for a mobile terminal 有权
标题翻译：移动终端的用户界面控制方法和系统
公开(公告)号：US07035629B2
公开(公告)日：2006-04-25
申请号：US10292761
申请日：2002-11-13
申请人： Satoru Fujii
发明人： Satoru Fujii
IPC分类号： H04H3/00
CPC分类号： H04M1/72519 , G06F3/0489 , H04W88/02
摘要： A mobile telephone and an external user interface processing device are connected to a communication network. The external user interface processing device stores a plurality of user interface programs. The mobile telephone transmits key operation event information to the external user interface processing device. The external user interface processing device executes a user interface program to produce a processing result of the key operation event information. The mobile telephone receives the processing result and controls the display according to the received processing result.
摘要翻译：移动电话和外部用户接口处理设备连接到通信网络。外部用户界面处理装置存储多个用户界面程序。移动电话将键操作事件信息发送到外部用户界面处理装置。外部用户界面处理装置执行用户界面程序以产生键操作事件信息的处理结果。移动电话接收处理结果并根据接收到的处理结果控制显示。

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