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. 发明专利

JP2005149527A System and method of facial authentication 审中-公开
标题翻译：系统和方法认证
公开(公告)号：JP2005149527A
公开(公告)日：2005-06-09
申请号：JP2004376398
申请日：2004-12-27
申请人： Toshiba Corp , 株式会社東芝
发明人： WAKASUGI TOMOKAZU , YAMAGUCHI OSAMU , SUZUKI KAORU , FUKUI KAZUHIRO , YUASA MAYUMI
IPC分类号： G06T7/00 , G06F15/00 , G06F21/20
摘要： PROBLEM TO BE SOLVED: To improve convenience by enabling a adjustment balance between performance of personal authentication and conformity, and strength to a variation of environment depending on the condition. SOLUTION: A system for facial authentication comprising a facial image input 41 for inputting a facial image of a user, a feature extractor 42 for extracting feature information from the facial image 42, 43, an authentication information storage 45 for storing corresponding pairs of registered facial image information for authentication and identification information inherent to the user, a collator 44 for collating the feature information with the registered information for authentication, an identification information acquisition part for acquiring the identification information from the user, and a re-collation controller for making the collator re-collate the registered facial image information for authentication, extracted from the authentication information storage 45 corresponding to the identification information acquired by the identification information acquisition part, with the feature information, when the collator, as a result of collation by the collator, cannot specify the registered information for authentication corresponding to the feature information. COPYRIGHT: (C)2005,JPO&NCIPI
摘要翻译：要解决的问题：通过使个人认证和符合性的性能之间的调整平衡以及根据条件的环境变化的强度来提高方便性。解决方案：一种用于面部认证的系统，包括用于输入用户的面部图像的面部图像输入41，用于从面部图像42,43提取特征信息的特征提取器42，用于存储相应对的认证信息存储器45 用于用户认证和识别信息的登记面部图像信息，用于将特征信息与用于认证的注册信息进行对照的整理器44，用于从用户获取识别信息的识别信息获取部分和重新对照控制器为了使归一化装置将由与识别信息取得部所取得的识别信息对应的认证信息存储部45提取出的认证用面部图像信息与特征信息进行重新整理，作为归类结果，整理器，不能指定用于与特征信息相对应的用于认证的注册信息。版权所有（C）2005，JPO＆NCIPI

22. 发明专利

JP2005046926A Service robot system, main robot and follower robot 审中-公开
标题翻译：服务机器人系统，主要机器人和机器人
公开(公告)号：JP2005046926A
公开(公告)日：2005-02-24
申请号：JP2003203747
申请日：2003-07-30
申请人： Toshiba Corp , 株式会社東芝
发明人： YOSHIMI TAKU , SUZUKI KAORU , YAMAMOTO DAISUKE , HIROKAWA JUNKO , NAKAMOTO SHUICHI
IPC分类号： B25J13/00 , B25J5/00
摘要： PROBLEM TO BE SOLVED: To provide a service robot system capable of providing various services at a low cost without enlarging or complicating a robot.
SOLUTION: In this service robot system, a main robot 20 is provided with a total management/operation planning module 41 for setting an operation plan on prescribed work based on instructions from a user U; a user communication module 42 for communicating information with the user U; a follower robot management module 47 for managing the positions and state of follower robots 50; and a follower robot control module 46 for controlling the operation of the follower robots 50. Further in the service robot system, the follower robot 50 is provided with a various service providing apparatus module 71 for performing prescribed work; a data response module 72 for transmitting information to the main robot 20; and an actuator module 73 for movement.
COPYRIGHT: (C)2005,JPO&NCIPI
摘要翻译：要解决的问题：提供一种能够以低成本提供各种服务的服务机器人系统，而不会使机器人增大或复杂化。解决方案：在该服务机器人系统中，主机器人20具有总管理/操作计划模块41，用于基于来自用户U的指令来设定规定工作的操作计划; 用户通信模块42，用于与用户U通信信息; 跟随机器人管理模块47，用于管理从动机器人50的位置和状态; 以及用于控制从动机器人50的操作的从动机器人控制模块46.另外在从动机器人系统中，从动机器人50设置有用于执行规定工作的各种服务提供装置模块71; 用于向主机器人20发送信息的数据响应模块72; 以及用于移动的致动器模块73。版权所有（C）2005，JPO＆NCIPI

23. 发明专利

JP2004350315A Communication terminal 审中-公开
公开(公告)号：JP2004350315A
公开(公告)日：2004-12-09
申请号：JP2004214952
申请日：2004-07-22
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI KAORU , TAKAHASHI KATSUMI , YAMAGUCHI SHOGO , WATANABE TOSHIAKI , IDA TAKASHI , KURATATE NAOAKI
IPC分类号： H04N7/14
摘要： PROBLEM TO BE SOLVED: To provide an image display apparatus for taking into account the safety expedients for a user without imposing physical torment on the user.
SOLUTION: The communication terminal includes: a signal input section 501; a signal output section 504; a symbol processing section 502 for converting its own talker signal into an its own talker code sequence; a signal processing section 503 for converting an opposite talker code sequence into an opposite talker signal; and a command separation section 605 that separates and extracts a command code sequence being a command to its own terminal from its own talker code sequence outputted from the symbol processing section 502, generates a control section corresponding to the command code sequence, and outputs a transmission code sequence excluding the command code sequence to the communication section 506 as a code sequence to be transmitted to an opposite station at the same time.
COPYRIGHT: (C)2005,JPO&NCIPI

24. 发明专利

JP2004336805A Communication terminal device 审中-公开
标题翻译：通信终端设备
公开(公告)号：JP2004336805A
公开(公告)日：2004-11-25
申请号：JP2004160331
申请日：2004-05-28
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI KAORU , TAKAHASHI KATSUMI , YAMAGUCHI SHOGO , WATANABE TOSHIAKI , IDA TAKASHI , KURATATE NAOAKI
IPC分类号： H04N5/225 , H04M1/00 , H04N7/14
摘要： PROBLEM TO BE SOLVED: To provide a communication terminal device which enables a photographer to grasp also the neighboring environments of the image to be transmitted and perform an appropriate and easy camera work.
SOLUTION: An imaging means 2001 covers a range wider than the image to be transmitted, and a display means 2002 displays the photographed images. The display means 2002 displays the photographed images in a display region 2105. Inside the display region 2105, there is a transmission region 2106, and an image inside the transmission region 2106 becomes an object-of-transmission image. An image triming means 2003 cuts out only an image corresponding to that in the transmission region 2106 out of the photographed images, and a coding means 2004 performs coding for transmitting the image cut out by the triming means 2003.
COPYRIGHT: (C)2005,JPO&NCIPI
摘要翻译：要解决的问题：提供一种通信终端设备，其使拍摄者能够掌握要发送的图像的相邻环境，并且执行适当且容易的相机工作。解决方案：成像装置2001覆盖比要发送的图像宽的范围，并且显示装置2002显示拍摄的图像。显示装置2002将拍摄的图像显示在显示区域2105中。在显示区域2105内，存在发送区域2106，并且发送区域2106内的图像成为发送对象图像。图像修整装置2003仅切出与拍摄图像中的发送区域2106中的图像相对应的图像，编码装置2004执行用于发送由修剪装置2003切出的图像的编码。版权所有（C））2005年，日本特许厅和NCIPI

25. 发明专利

JP2004320796A Communication terminal device 审中-公开
公开(公告)号：JP2004320796A
公开(公告)日：2004-11-11
申请号：JP2004160321
申请日：2004-05-28
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI KAORU , TAKAHASHI KATSUMI , YAMAGUCHI SHOGO , WATANABE TOSHIAKI , IDA TAKASHI , KURATATE NAOAKI
IPC分类号： H04N7/14 , H04M11/00
摘要： PROBLEM TO BE SOLVED: To provide a communication terminal device in which a required encoding rate can be appropriately selected.
SOLUTION: A moving image of a party is displayed on a screen 1401, material transmitted from the party is displayed on a screen 1402, and an image from a present station is picked up by a camera 1403, encoded and then transferred from an antenna 1406 to an opposite station by radio. Audio is also similarly captured from a microphone 1407 and transferred from the antenna 1406 to the opposite station, and voices of an opposite speaking party can be obtained via a speaker 1408. Then, the screen 1401 for displaying motion pictures includes a low-resolution screen and the screen 1402 for displaying still pictures includes a high-resolution screen.
COPYRIGHT: (C)2005,JPO&NCIPI

26. 发明专利

JP2000076260A Database driving device and method therefor 有权
标题翻译：数据库驱动设备及其方法
公开(公告)号：JP2000076260A
公开(公告)日：2000-03-14
申请号：JP24147298
申请日：1998-08-27
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI KAORU
IPC分类号： G06F3/048 , G06F3/00 , G06F17/30
摘要： PROBLEM TO BE SOLVED: To conduct the designation state of a designation object satisfying a retrieval condition given by the AND of an object designation key designating a retrieval object and a state designation key designating the state of the object. SOLUTION: In the database driving device/method, a different object in a database 6, which can take a state designated by an object designation key, is retrieved when an object in the database 6, which is designated by an object designation key, cannot take the state designated by the state designation key. Parts for making the designation object take the designation state are allocated based on the morphological or functional similarity of constitution parts of the different object and the designated object. A procedure prepared for making the different object realize the designation state based on peculiar part information is applied to the allocated part of the designation object. Thus, a state that the designation object realizes the designation state is visually displayed.
摘要翻译：要解决的问题：进行满足由指定检索对象的对象指定键和指定对象的状态的状态指定键的AND给出的检索条件的指定对象的指定状态。解决方案：在数据库驱动设备/方法中，当由对象指定键指定的数据库6中的对象不能被检索时，可以采用由对象指定键指定的状态的数据库6中的不同对象取状态指定键指定的状态。基于不同对象和指定对象的构成部分的形态或功能相似度来分配用于使指定对象采用指定状态的部分。将用于使不同对象实现基于特定部分信息的指定状态的程序应用于指定对象的分配部分。因此，可视地显示指定对象实现指定状态的状态。

27. 发明专利

JP2012189906A Voice discrimination device, voice discrimination method and voice discrimination program 有权
标题翻译：语音识别设备，语音识别方法和语音识别程序
公开(公告)号：JP2012189906A
公开(公告)日：2012-10-04
申请号：JP2011054758
申请日：2011-03-11
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI KAORU , SAKAI MASARU , KIDA YUSUKE
IPC分类号： G10L11/00 , G10L15/20 , G10L21/02
CPC分类号： G10L25/84 , G10L21/0208 , G10L21/0232 , G10L25/18 , G10L2021/02166
摘要： PROBLEM TO BE SOLVED: To provide a voice discrimination device that eliminates an effect of masking sound without eliminating a basic component of user's voice from an acoustic signal.SOLUTION: A voice discrimination device according to an embodiment comprises: weight providing means for providing weight according to each frequency band, based on a frequency spectrum of a first acoustic signal including a user's voice and a frequency spectrum of a second acoustic signal including a masking sound; feature extraction means for using the weight provided according to each frequency band by the weight providing means to extract a feature amount from the frequency spectrum of the first acoustic signal; and voice/non-voice discrimination means for discriminating voice/non-voice of the first acoustic signal, based on the feature amount extracted by the feature extraction means.
摘要翻译：要解决的问题：提供一种消除掩蔽声音的效果的声音识别装置，而不会从声信号中消除用户声音的基本分量。解决方案：根据实施例的语音识别装置包括：权重提供装置，用于根据包括用户的语音和第二声信号的频谱的第一声信号的频谱，根据每个频带提供权重包括掩蔽声; 特征提取装置，用于通过权重提供装置使用根据每个频带提供的权重，从第一声信号的频谱中提取特征量; 以及用于基于由特征提取装置提取的特征量来区分第一声信号的语音/非声音的语音/非语音识别装置。版权所有（C）2013，JPO＆INPIT

28. 发明专利

JP2009080309A Speech recognition device, speech recognition method, speech recognition program and recording medium in which speech recogntion program is recorded 审中-公开
标题翻译：语音识别装置，语音识别方法，语音识别程序和语音识别程序记录的记录媒体
公开(公告)号：JP2009080309A
公开(公告)日：2009-04-16
申请号：JP2007249648
申请日：2007-09-26
申请人： Toshiba Corp , 株式会社東芝
发明人： SUZUKI KAORU , DOI MIWAKO , KOGA TOSHIYUKI , YAMAMOTO KOICHI
IPC分类号： G10L15/20 , G10L15/08 , G10L15/10 , G10L15/28 , G10L17/00 , G10L21/02
摘要： PROBLEM TO BE SOLVED: To detect a time period when noise is dominant, in sound source locating process, and to perform suitable processing in this time period in speech recognition process. SOLUTION: Phase difference and power are calculated for each frequency component from first and second sound signals which are captured in two points, and a scatter diagram in which frequency and phase difference for each frequency component are set as coordinates is created. Arrangement of the frequency component for showing predetermined linearity on the scatter diagram is detected, together with a straight line score according to the power of the frequency component. The arrangement in which the straight line score is a predetermined threshold or more, is detected as the straight line for indicating existence of the sound source. A sound source stream composed of information of the straight lines and the straight lines scores etc. is extracted, and reliability information is attached for each time of the sound source stream, based on height of the straight line score for each time of the sound source stream. COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：在声源定位过程中检测噪声占优的时间段，并在语音识别过程中在该时间段内执行适当的处理。解决方案：针对从两点捕获的第一和第二声音信号的每个频率分量计算相位差和功率，并且创建将每个频率分量的频率和相位差设置为坐标的散点图。检测用于在散点图上显示预定线性度的频率分量的布置以及根据频率分量的功率的直线得分。检测直线得分为预定阈值或更多的布置作为用于指示声源的存在的直线。提取由直线和直线得分等的信息构成的声源流，并且基于声源的每次的直线得分的高度，附加声源流的每次的可靠性信息流。版权所有（C）2009，JPO＆INPIT

29. 发明专利

JP2008103875A Synthetic d/a converter and magnetic resonance imaging device by it 审中-公开
标题翻译：合成D / A转换器和磁共振成像装置
公开(公告)号：JP2008103875A
公开(公告)日：2008-05-01
申请号：JP2006283429
申请日：2006-10-18
申请人： Toshiba Corp , Toshiba Medical Systems Corp , 東芝メディカルシステムズ株式会社 , 株式会社東芝
发明人： SUZUKI KAORU
IPC分类号： H03M1/10 , A61B5/055 , G01R33/385
摘要： PROBLEM TO BE SOLVED: To provide a D/A converter holding down a cost, being operated at a high speed and having a high accuracy and a high resolution by using the D/A converter obtaining high speed operation at a low cost and having the small number of bits.
SOLUTION: The D/A converter has a first D/A converter inputting N1 bits of N bits digital data N from an MSB to the LSB side and an accuracy compensating-value memory storing preset digital compensating values NcN to each of the digital data N while using the digital data N of the N bits as an address and outputting the digital compensating values NcN at least N2=(N-N1+2) bits corresponding to the digital data N by inputting the digital data N. The D/A converter further has a second D/A converter at N2 bits connected to an output from the accuracy compensating-value memory and an amplifier amplifying the output from the first D/A converter at an amplification factor of 2
(N-N1) . The D/A converter further has an adder adding the output from the amplifier and the output from the second D/A converter. A synthetic D/A converter uses the result of the output from the adder as the analog converting value of the digital input data N. A magnetic resonance imaging device consists of the synthetic D/A converter.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：为了提供一种降低成本的D / A转换器，通过使用D / A转换器以低成本获得高速运行，高速运行并具有高精度和高分辨率并且具有少量的位。解决方案：D / A转换器具有从MSB至LSB侧输入N位数字数据N的N1位的第一D / A转换器，以及将预置的数字补偿值NcN存储到每一个的精度补偿值存储器数字数据N，同时使用N位的数字数据N作为地址，并通过输入数字数据N输出对应于数字数据N的至少N2 =（N-N1 + 2）位的数字补偿值NcN。D A转换器还具有连接到精度补偿值存储器的输出的N 2位的第二D / A转换器和放大倍数为2×（N-1）的第一D / A转换器的输出的放大器， N1）。 D / A转换器还具有将来自放大器的输出和来自第二D / A转换器的输出相加的加法器。合成D / A转换器使用加法器的输出结果作为数字输入数据N的模拟转换值。磁共振成像装置由合成D / A转换器组成。版权所有（C）2008，JPO＆INPIT

30. 发明专利

JP2008079255A Acoustic signal processing apparatus, acoustic signal processing method, and acoustic signal processing program 有权
标题翻译：声音信号处理装置，声音信号处理方法和声音信号处理程序
公开(公告)号：JP2008079255A
公开(公告)日：2008-04-03
申请号：JP2006259343
申请日：2006-09-25
申请人： Toshiba Corp , 株式会社東芝
发明人： KOGA TOSHIYUKI , SUZUKI KAORU
IPC分类号： H04R3/00 , G10L21/02
CPC分类号： H04R3/005 , H04R2430/20
摘要： PROBLEM TO BE SOLVED: To provide an acoustic signal processing apparatus, acoustic signal processing method and acoustic signal processing program, for sound source localization and sound source separation, capable of dealing with sound sources as many as or more than microphones while relaxing a limitation to the sound sources rather than the prior art. SOLUTION: The acoustic signal processing apparatus comprises a voting means which performs Hough transformation on a group of dots forming two-dimensional data, respectively, generates a plurality of loci corresponding to each of dots, and adds a betting value at a position in a Hough voting space where the plurality of loci pass, while varying the voting value based on a level difference between first and second signal levels indicated by two frequency decomposition information items, respectively, when adding the voting value. COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：为了提供用于声源定位和声源分离的声信号处理装置，声信号处理方法和声信号处理程序，能够处理多个或多于麦克风的声源，同时放松对声源的限制，而不是现有技术。解决方案：声信号处理装置包括一个投票装置，分别对形成二维数据的一组点执行霍夫变换，产生与每个点对应的多个轨迹，并将一个下注值加到一个位置在多个轨迹通过的霍夫投票空间中，在添加投票值时，分别基于由两个频率分解信息项指示的第一和第二信号电平之间的电平差来改变投票值。版权所有（C）2008，JPO＆INPIT

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