公开(公告)号：JP2013029690A

公开(公告)日：2013-02-07

申请号：JP2011166071

申请日：2011-07-28

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： IKEDA TOMOO ,  NAGAO MANABU ,  NISHIYAMA OSAMU ,  SUZUKI HIROKAZU ,  UENO AKITSUGU ,  SHIMOGOORI NOBUHIRO

IPC: G10L17/00 ,  G10L15/00

CPC classification number: G10L21/028 ,  G10L15/26

Abstract: PROBLEM TO BE SOLVED: To provide a speaker classification device in which linguistic features contained in a speech are utilized to detect erroneous classification caused by sonic features.SOLUTION: A speaker classification device of an embodiment comprises sonic classification means, linguistic feature extraction means and erroneous classification detection means. The sonic classification means classifies speeches contained in inputted sonic signals for each speaker by utilizing sonic features extracted from the sonic signals and acquires a classification result. The linguistic feature extraction means acquires a character string representing contents of the speech and utilizes the character string to extract linguistic features of the speaker contained in the classification result. The erroneous classification detection means discriminates whether or not the character string representing the contents of the speech meets the linguistic features of the speaker classifying the speech in the classification result and, if not, discriminates the speech as a speech erroneously classified by the sonic classification means.

Abstract translation: 要解决的问题：提供一种扬声器分类装置，其中包含在语音中的语言特征被用于检测由声音特征引起的错误分类。 解决方案：实施例的扬声器分类装置包括声音分类装置，语言特征提取装置和错误分类检测装置。 声音分类装置通过利用从声音信号中提取的声音特征对每个扬声器输入的声音信号中包含的演讲进行分类，并获得分类结果。 语言特征提取装置获取表示语音内容的字符串，并利用字符串来提取分类结果中包含的说话者的语言特征。 错误分类检测装置判断代表语音内容的字符串是否符合对分类结果中的语音进行分类的语音特征，如果不是，则将该语音识别为由声音分类装置错误地分类的语音 。 版权所有（C）2013，JPO＆INPIT

公开(公告)号：JP2012129950A

公开(公告)日：2012-07-05

申请号：JP2010282152

申请日：2010-12-17

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： UENO AKITSUGU ,  SHIMOGOORI NOBUHIRO ,  IKEDA TOMOO

IPC: H04N7/15 ,  H04M3/56

CPC classification number: H04N7/15 ,  H04L29/06 ,  H04L65/403 ,  H04L65/605 ,  H04L67/325 ,  H04N7/147

Abstract: PROBLEM TO BE SOLVED: To provide a conference support device which displays information on delay occurring on the other side of a conference by information extraction processing, which facilitates understanding the situation of the other side, thereby making the progress of the conference smooth.SOLUTION: The conference support device of this embodiment, which supports a conference performed between at least two or more terminals, comprises delay means which applies delay caused by the information extraction processing on first voice data obtained by one terminal to the first voice data; and delay information video generation means which generates delay information video obtained by visualizing information on the delay applied to the first voice data by the delay means.

Abstract translation: 要解决的问题：提供一种会议支持装置，其通过信息提取处理显示会议另一侧发生的延迟的信息，这有助于理解对方的情况，从而使会议的进展顺利 。 解决方案：本实施例的支持在至少两个或更多个终端之间执行的会议的会议支持设备包括延迟装置，该延迟装置将由一个终端获得的第一语音数据的信息提取处理引起的延迟应用于第一语音 数据; 以及延迟信息视频产生装置，其产生延迟信息视频，该视频通过可视化延迟装置对应用于第一语音数据的延迟的信息而获得。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012073396A

公开(公告)日：2012-04-12

申请号：JP2010217898

申请日：2010-09-28

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： IKEDA TOMOO ,  SHIMOGOORI NOBUHIRO ,  UENO AKITSUGU

IPC: G10L15/22 ,  G06F3/16 ,  G10L15/00 ,  G10L15/06

CPC classification number: G10L15/1807 ,  G10L15/04

Abstract: PROBLEM TO BE SOLVED: To perform highlighting corresponding to a usage situation and a learning situation of a user.SOLUTION: A conference support device comprises a pronunciation recognition information storage part, a word emphasis determination part and a display content generation part. The pronunciation recognition information storage part associates a word with pronunciation information and a pronunciation recognition frequency by word and stores it as storage information. The word emphasis determination part determines if a second set consisting of a second word and pronunciation information that matches a first set consisting of a first word and pronunciation information is included and shows information if the first word should be highlighted based on the pronunciation recognition frequency of the second word when the second set is included. If the first word should be highlighted, the word emphasis determination part generates emphasis determination information including emphasis level that shows a degree of highlighting decided according to the pronunciation recognition frequency of the second word. If the first word should be highlighted based on the emphasis determination information, the display content generation part generates a highlighted character string which is the first word combined with a mark showing higher emphasis level should be highlighted stronger.

Abstract translation: 要解决的问题：执行与用户的使用情况和学习情况相对应的突出显示。 解决方案：会议支持设备包括发音识别信息存储部分，字重点确定部分和显示内容生成部分。 发音识别信息存储部分将单词与发音信息和发音识别逐字地相关联，并将其存储为存储信息。 单词强调确定部分确定包括第二个单词和与第一个单词和发音信息组成的第一组匹配的发音信息的第二组是否包含第一个单词，并且如果第一个单词应该基于发音识别频率 包括第二组的第二个字。 如果要突出显示第一个单词，则单词强调确定部分产生强调确定信息，其包括强调级别，该强调级别显示根据第二单词的发音识别频率确定的高亮度。 如果基于强调确定信息突出显示第一个单词，则显示内容生成部分将生成突出显示的字符串，该第一个字符串与显示较高强度级别的标记组合应该被强调。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2006155330A

公开(公告)日：2006-06-15

申请号：JP2004346515

申请日：2004-11-30

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： UMEKI HIDEO ,  IKEDA TOMOO ,  TSUBOI SOUGO

IPC: G06F13/00 ,  G06F17/30

CPC classification number: G06Q10/10

Abstract: PROBLEM TO BE SOLVED: To provide a relationship information generation system, which generates relationship information that allows users to understand relationship between an information resource and another one generated or selected based on it corresponding to each of the information resources.
SOLUTION: The relationship information generation system has a determination means (11) for determining an action, which is used when a user creates or selects a second information resource (Rd) referring to at least one first information resource (Rs), and a relationship information generation means (13) for generating first relationship information (Lsd), which includes a first explanation that explains relationship from the first information resource (Rs) to the second information resource (Rd), and second relationship information (Lds), which includes a second explanation that explains relationship from the second information resource (Rd) to the first information resource (Rs) according to the determined action.
COPYRIGHT: (C)2006,JPO&NCIPI

Abstract translation: 要解决的问题：提供一种关系信息生成系统，其生成允许用户基于与每个信息资源相对应地生成或选择的另一个生成或选择的信息资源之间的关系的关系信息。 关系信息生成系统具有确定装置（11），用于确定当用户创建或选择参考至少一个第一信息资源（Rs）的第二信息资源（Rd）时使用的动作， 以及用于生成第一关系信息（Lsd）的关系信息生成装置（13），其包括解释从第一信息资源（Rs）到第二信息资源（Rd）的关系的第一解释，以及第二关系信息（Lds） ，其包括根据确定的动作来解释从第二信息资源（Rd）到第一信息资源（Rs）的关系的第二解释。 版权所有（C）2006，JPO＆NCIPI

公开(公告)号：JP2004320542A

公开(公告)日：2004-11-11

申请号：JP2003113189

申请日：2003-04-17

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： EZAKA NAOKI ,  GOTO MASATAKA ,  IKEDA TOMOO

IPC: H04L12/28 ,  H04B7/155 ,  H04B7/26

Abstract: PROBLEM TO BE SOLVED: To provide a radio relaying device and a radio communication relaying method for putting together or distributing transmission data among radio communication devices.
SOLUTION: The radio relaying device relays radio communications among a plurality of radio communication devices. At first, a first service and configuration information representing the configuration of a radio communication device associated with the service are established at the radio relaying device. A service available by the radio communication device is searched according to a service search procedure. The radio communication device associated with the searched service is identified based on the configuration information, and connection with the identified radio communication device is activated. Radio communication channels between radio communication devices for starting the connection are put together or distributed.
COPYRIGHT: (C)2005,JPO&NCIPI

公开(公告)号：JP2004128706A

公开(公告)日：2004-04-22

申请号：JP2002287457

申请日：2002-09-30

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： GOTO MASATAKA ,  EZAKA NAOKI ,  IKEDA TOMOO

IPC: H04L12/66 ,  H04B7/26 ,  H04L12/28 ,  H04L12/46

Abstract: PROBLEM TO BE SOLVED: To provide a wireless relay apparatus and a wireless communication system capable of providing and utilizing a wireless service even in a range in excess of a wireless communication range decided by the standard.
SOLUTION: The wireless communication system is provided with a BT user terminal 1 and a BT service apparatus 2 each having a wireless function in compliance with the specification of the Bluetooth (R); and a plurality of relay apparatuses 3 configured similarly to the configuration shown in Figure. Each relay apparatus 3 is provided with a Bluetooth (R) communication section performing wireless communication in compliance with the specification of the Bluetooth (R), a CoD (class of device) setting section, an SDP (service discovery protocol) relay section, a channel relay section, and a TCP/IP communication section. Since the BT user terminal 1 receives provision of the service by the BT service apparatus 2 over a range far broader than a communication distance decided by the specification of the Bluetooth (R), the convenience of users is enhanced.
COPYRIGHT: (C)2004,JPO

公开(公告)号：JP2014142501A

公开(公告)日：2014-08-07

申请号：JP2013011221

申请日：2013-01-24

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： NAKATA KOTA ,  ASHIKAWA TAIRA ,  IKEDA TOMOO ,  UENO AKITSUGU ,  NISHIYAMA OSAMU

IPC: G10L15/04 ,  G10L13/00 ,  G10L19/00 ,  H04N7/173

CPC classification number: G10L15/22 ,  G10L2015/221 ,  G10L2015/225

Abstract: PROBLEM TO BE SOLVED: To provide a text reproduction device, a method and a program for accurately locating the start of a voice.SOLUTION: A reproduction part reproduces voice data. A first acquisition part acquires a text input by a user. A setting part sets a sectioning position for sectioning the text in accordance with an input from a user during the reproduction of the voice data. A second acquisition part acquires the reproducing position of the voice data reproduced when the sectioning position is set. An estimation part performs the matching of a text in a periphery of the sectioning position and voice data in a periphery of the reproducing position, and estimates the more accurate position of the voice data corresponding to the sectioning position. A correction part corrects the reproducing position into the estimated more accurate position of the voice data, and when the sectioning position is designated by the user, performs setting so that the reproduction of the voice data can be started from the corrected reproducing position.

Abstract translation: 要解决的问题：提供一种用于准确定位语音开始的文本再现装置，方法和程序。解码：再现部分再现语音数据。 第一采集部件获取用户输入的文本。 设置部分在再现语音数据期间根据来自用户的输入设置用于对文本进行分段的分段位置。 第二获取部分获取当设置分割位置时再现的声音数据的再现位置。 估计部分执行再现位置周边的分割位置的周边的文本和语音数据的匹配，并且估计对应于分割位置的语音数据的更准确的位置。 校正部分将再现位置校正为估计的更精确的语音数据位置，并且当用户指定分割位置时，执行设置，使得能够从校正的再现位置开始语音数据的再现。

公开(公告)号：JP2014038132A

公开(公告)日：2014-02-27

申请号：JP2012179023

申请日：2012-08-10

Applicant: Toshiba Corp ,  株式会社東芝

Inventor： NISHIYAMA OSAMU ,  ASHIKAWA TAIRA ,  IKEDA TOMOO ,  UENO AKITSUGU ,  NAKATA KOTA

IPC: G10L17/00

CPC classification number: G10L17/02 ,  G10L17/06

Abstract: PROBLEM TO BE SOLVED: To provide information that can easily set a speaker name to utterance data of the speaker.SOLUTION: A first reception part 24 of an information processor 12 receives voice data including utterance data of a speaker. A division part 25 divides the voice data to each utterance data. A giving part 26 attaches speaker identification information to the utterance data on the basis of an acoustic feature of the utterance data. A second reception part 28 receives from a user instruction information showing utterance data of a speaker name setting object in the utterance data included in the voice data. A generation part 30 generates a candidate list showing candidates for a speaker name set in utterance data specified by instruction information by the user on the basis of operation history information obtained by associating at least utterance identification information of the utterance data with the given speaker identification information, and with the speaker name set by the user for the utterance data specified by the utterance identification information.

Abstract translation: 要解决的问题：提供可以容易地将扬声器名称设置为扬声器的话语数据的信息。解决方案：信息处理器12的第一接收部分24接收包括说话者的话语数据的语音数据。 分割部分25将语音数据划分为每个话音数据。 给出部分26基于发声数据的声学特征将说话者识别信息附加到话音数据。 第二接收部分28从用户指示信息中接收表示语音数据中包含的话音数据中的扬声器名称设定对象的说话数据。 生成部30基于通过将发话数据的发音识别信息与给定的说话者识别信息至少相关联而获得的操作历史信息，生成候选列表，其中显示由用户指定的由话音信息指定的话语数据中设置的讲话者姓名的候选列表 并且由用户为由话音识别信息指定的话语数据设置的扬声器名称。

公开(公告)号：JP2000137683A

公开(公告)日：2000-05-16

申请号：JP30998098

申请日：1998-10-30

Applicant: TOSHIBA CORP

Inventor： SUGIKAWA AKIHIKO ,  IKEDA TOMOO

IPC: G06F7/24 ,  G06F3/00 ,  G06F3/048 ,  G06F13/00 ,  G06F15/00 ,  H04N1/00

Abstract: PROBLEM TO BE SOLVED: To provide an information processor for easily arranging the points of a talk, and for easily understanding both the flow of the talk and the points of the talk for shared data with conversation as contents. SOLUTION: This method for processing shared data has a function for sharing prescribed data by exchanging information with one or more information processors. The shared data are displayed in the first area of a display screen, and specific data are designated from among the data displayed in the first area, and classification attributes to be applied to the designated data are designated. Then, the designated data are made correspond to at least information for identifying the designated classification attributes and stored as classified data, and the stored classified data are classified for each classification attribute and displayed in the second area of the display screen.

公开(公告)号：JPH09218770A

公开(公告)日：1997-08-19

申请号：JP2672396

申请日：1996-02-14

Applicant: TOSHIBA CORP

Inventor： CHINO TETSURO ,  IKEDA TOMOO ,  KONO YASUYUKI

IPC: G06F3/02 ,  G06F3/048 ,  G06F3/14 ,  G06F3/16 ,  G06F17/28

Abstract: PROBLEM TO BE SOLVED: To relieve the burden of a user by utilizing an agreeable response playing an important roll in a conversation or utilizing expression for requesting the agreeable response to the user. SOLUTION: An interactive communication control part 5 controls the operation of at least one among an input part 1, an output part 3, an interactive management problem solving part 2, an aggreeable resonse expression recognizing part 4 and an aggreeable response expression generating part 6 based on at least one among input message information obtained from the input part 1, agreeable response input information obtained from the aggreeable response expression recognizing part 4 and aggreeable reesponse expecting information obtained from the aggreeable response expression generating part 6. When aggreeable response requesting expression to the user is presented in accordance with the instruction of the interactive communication control part 5 through a certain output message, aggreeable response expression is given to the configuration part of output message information which is presented eariest if aggreeable response request expression can be generated by an aggreeable response request expression generating rule.