-
公开(公告)号：KR1020120138273A
公开(公告)日：2012-12-26
申请号：KR1020110057618
申请日：2011-06-14
Applicant: 한국전자통신연구원
CPC classification number: G06F17/289 , G10L13/08 , G10L15/26
Abstract: PURPOSE: An automatic translation method and an apparatus for the same using sentence similarity and sentence frame similarity are provided to examine sentence similarity and sentence frame similarity of recognized voice and search translated sentences from translation memory, thereby automatically performing translation not using complex algorithms and many resources. CONSTITUTION: A language processor(110) processes an input sentence produced by recognizing input voice and outputs a keyword. A sentence similarity examiner(120) searches a candidate sentence similar to the input sentence from translated sentences consisting of pairs of the first language and second language sentences. A sentence frame similarity examiner(205) searches a framed sentence of the candidate sentence. A word changer(140) compares the input sentence with the framed sentence, and then finds and changes different words. A keyword re-examiner(150) examines similarity using a selected keyword in the framed sentence. [Reference numerals] (100) Voice recognition part; (110) Language processor; (120) Similarity examiner; (140) Word changer; (150) Keyword re-examiner; (160) Word unit interpretation unit; (170) Voice synthesizing unit; (180) Control unit; (190) Screen output unit; (200) Interpretation memory; (205) Sentence frame similarity examiner
Abstract translation: 目的：提供一种使用句子相似度和句子相似度的自动翻译方法和装置，用于检查翻译记忆库中识别的语音和搜索翻译句子的句子相似性和句子帧相似度，从而自动执行不使用复杂算法的翻译和许多 资源。 构成：语言处理器（110）处理通过识别输入语音产生的输入句子并输出关键字。 句子相似性检查器（120）从由第一语言和第二语言句子对组成的翻译句子中搜索类似于输入句子的候选句子。 句子相似度检查器（205）搜索候选句子的框架句子。 换字器（140）将输入的句子与框架句子进行比较，然后找到并改变不同的单词。 关键词重新审查者（150）使用框架句中的选定关键字检查相似性。 （附图标记）（100）语音识别部; （110）语言处理器; （120）相似性审查员; （140）换字机; （150）关键词审查员; （160）单位解读单位; （170）语音合成单元; （180）控制单元 （190）屏幕输出单元; （200）解释记忆; （205）句子相似度检查者
-
公开(公告)号：KR101134467B1
公开(公告)日：2012-04-13
申请号：KR1020090068268
申请日：2009-07-27
Applicant: 한국전자통신연구원
IPC: G06F17/28 , G10L15/18 , G10L15/183 , G10L15/26
Abstract: 본 발명은 자동 통역 시스템에 적용되는 의미 표현 처리 기법에 관한 것으로, 입력되는 음성에 대응하는 음성 인식 결과의 단어열을 의미 표현으로 변환하고, 변환된 의미 표현을 기 구축된 의미 표현 집합 데이터베이스를 참조하여 검색하며, 검색 결과에 따라 최종 의미 표현을 결정하고, 결정된 최종 의미 표현을 최종 문장으로 생성 및 출력함으로써, 사용자 의도가 반영된 의미 표현을 결정하여 자동 통역 시스템의 성능을 향상시킬 수 있는 것이다.
자동 통역 시스템, 음성 인식, 의미 표현-
公开(公告)号：KR1020110038448A
公开(公告)日：2011-04-14
申请号：KR1020090095741
申请日：2009-10-08
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2854
Abstract: PURPOSE: An automatic interpretation terminal, a service, a system and method for servicing automatic interpretation are provided to supply rapid and exact interpretation service by directly performing interpretation and relay interpretation by utilizing a plurality of interpretation supporters and providing an interpretation result to a terminal of a user. CONSTITUTION: A communication unit(300) receives interpretation request from a user. The communication unit transmits an interpretation result according to the interpretation request. A interpretation applicant information DB(306) stores a list information of the interpretation supporters capable of performing interpretation as a target language. A server control unit(304) searches interpretation supporter capable of interpreting the request target language.
Abstract translation: 目的：提供自动解释终端，服务，系统和方法来提供快速准确的口译服务，通过利用多个解释支持者直接进行解释和中继解释，并将解释结果提供给终端 一个用户 构成：通信单元（300）从用户接收解释请求。 通信单元根据解释请求发送解释结果。 解释申请者信息DB（306）存储能够进行解释的解释支持者的列表信息作为目标语言。 服务器控制单元（304）搜索能够解释请求目标语言的解释支持者。
-
公开(公告)号：KR1020110027549A
公开(公告)日：2011-03-16
申请号：KR1020100066675
申请日：2010-07-12
Applicant: 한국전자통신연구원
Abstract: PURPOSE: An electro-optic modulating device is provided to form vertical PN junctions or vertical PIN junctions in an optical waveguide, thereby increasing a change of an effective refractive index during a device operation. CONSTITUTION: A semiconductor film(30) configuring an optical waveguide(WG) is arranged on a substrate(10). The optical waveguide comprises the first slab part(SP1), the second slab part(SP2), and a lip part(RP). The lip part includes a thickness thicker than the first and second slab parts. The first and second doping areas(D1,D2) are formed on the first and second slab parts respectively. A vertical doping area(50) configuring a vertical structure is formed in the lip part.
Abstract translation: 目的：提供电光调制装置以在光波导中形成垂直PN结或垂直PIN结，从而在器件操作期间增加有效折射率的变化。 构成：构成光波导（WG）的半导体膜（30）配置在基板（10）上。 光波导包括第一板坯部（SP1），第二板坯部（SP2）和唇部（RP）。 唇部包括比第一和第二板坯部分厚的厚度。 第一和第二掺杂区域（D1，D2）分别形成在第一和第二平板部件上。 在唇部形成垂直结构的垂直掺杂区域（50）。
-
公开(公告)号：KR1020110023442A
公开(公告)日：2011-03-08
申请号：KR1020090081339
申请日：2009-08-31
Applicant: 한국전자통신연구원
CPC classification number: G02B6/12004 , G02B6/131 , G02B6/136 , G02B2006/121 , H01L31/0352
Abstract: PURPOSE: A waveguide photo detector is provided to maximize the electrical features of a doped layer for connecting between a waveguide layer in a lower part of an absorbing layer and a waveguide layer of a lower part of a second electrode. CONSTITUTION: A waveguide photo detector comprises the following units. A waveguide layer is expanded in a first direction. An absorbing layer(30) is formed on the waveguide layer. The first electrode of the absorbing layer is formed on the waveguide layer. A second electrode is separated from the first electrode and the absorbing layer in a second direction crossing the first direction. At least one bridge electrically connects the absorbing layer with the second electrode.
Abstract translation: 目的：提供一种波导光电检测器，以最大化掺杂层的电气特征，用于连接吸收层下部的波导层和第二电极下部的波导层。 构成：波导光电检测器包括以下单元。 波导层在第一方向上扩展。 在波导层上形成吸收层（30）。 吸收层的第一电极形成在波导层上。 第二电极与第一电极和吸收层沿与第一方向交叉的第二方向分离。 至少一个桥将吸收层与第二电极电连接。
-
Patent Agency Ranking
公开(公告)号：KR1020100137873A
公开(公告)日：2010-12-31
申请号：KR1020090056120
申请日：2009-06-23
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A speaker adaptation system and a method thereof are provided to utilize the cumulative variable for obtaining enough statistics for the non-instruction adaptation in voice recognitioin process without performing an adaptation training thereby enabling to gradual adaptation. CONSTITUTION: A characteristic detecting part(110) extracts an eigenvector from a voice signal. A sound model storage(120) stores an acoustic model consisting of a recursive tree. A conversion parameter class determiner(130) produces gaussian posteriori probability of a candidate state based on the eigenvector and the sound model and determines the cumulative variable and a conversion parameter class based on the gaussian posterior probability. A sound model updater(140) produces the conversion parameter based on the conversion parameter class and cumulative variable and renews the acoustic model.
Abstract translation: 目的：提供一种扬声器适应系统及其方法，以利用该累积变量来获得用于语音识别过程中的非指令适配的足够的统计量，而不进行适应训练，从而能够逐渐适应。 构成：特征检测部（110）从语音信号中提取特征向量。 声音模型存储（120）存储由递归树组成的声学模型。 转换参数类确定器（130）基于特征向量和声音模型产生候选状态的高斯后验概率，并且基于高斯后验概率确定累积变量和转换参数类。 声音模型更新器（140）基于转换参数类和累积变量产生转换参数，并更新声学模型。
-
公开(公告)号：KR101000941B1
公开(公告)日：2010-12-13
申请号：KR1020080105199
申请日：2008-10-27
Applicant: 한국전자통신연구원
IPC: H01L31/028 , H01L27/04 , H01L31/18 , H01L27/14
CPC classification number: H01L31/028 , H01L21/02381 , H01L21/0245 , H01L21/02532 , H01L21/02592 , H01L21/0262 , H01L21/02667 , H01L31/103 , H01L31/1808 , H01L31/1872 , Y02E10/50 , Y02P70/521
Abstract: 버퍼층 없이 게르마늄 에피층을 형성할 수 있는 게르마늄 광 검출기 및 그 제조방법이 제공된다. 기판 상에 저온에서 비정질 게르마늄층을 형성하고, 상기 비정질 게르마늄층을 고온으로 승온하여 결정화하고, 상기 결정화된 게르마늄층 상에 게르마늄 에피층을 형성한다.
게르마늄 광 검출기, 비정질, 버퍼층, 저진공-
公开(公告)号：KR100932538B1
公开(公告)日：2009-12-17
申请号：KR1020070128929
申请日：2007-12-12
Applicant: 한국전자통신연구원
Inventor： 김상훈
CPC classification number: G10L13/08
Abstract: 본 발명은 은닉 마르코브 모델(Hidden Markov Model, HMM) 기반 음성 합성 방법 및 장치에 관한 것이다. HMM 모델의 상태별 음성 파라미터 인스턴스들이 양자화된 코드워드들 중에서, 입력된 텍스트로부터 종래의 방법으로 생성된 음성 파라미터와 가장 가까운 거리의 코드워드를 탐색한다. 탐색된 코드워드와 종래의 방법으로 생성된 음성 파라미터간의 거리가 임계치 이하이면, 탐색된 코드워드를 최종 음성 파라미터로서 출력하고, 그렇지 않으면 종래의 방법으로 생성된 음성 파라미터를 최종 음성 파라미터로서 그대로 출력한다. 최종 음성 파라미터를 처리하여 입력된 텍스트에 대한 최종 합성음을 생성한다.
Abstract translation: 本发明涉及一种隐藏马尔科探针模型（隐马尔可夫模型，HMM）的语音合成方法和设备。 间的HMM模型实例的特定条件的语音参数被量化的代码字，并且搜索在从输入文本的传统方法生成的语音参数最接近的码字。 如果所找到的码字如下阈值的传统方法生成的语音参数之间的距离，并输出所找到的码字作为最终语音参数，如果没有，输出作为通过常规方法生成的语音参数，作为最后的语音参数 。 并产生用于文本输入处理合成为最终的语音参数的最后。
-
公开(公告)号：KR1020090065866A
公开(公告)日：2009-06-23
申请号：KR1020070133391
申请日：2007-12-18
Applicant: 한국전자통신연구원
CPC classification number: G06K9/00335 , G06K9/00288
Abstract: A method and a device for discriminating a lip motion image are provided to enable labeling on the online network and realize SVM(Support Vector Machine) pattern classification. Face motion image frames received from an imaging unit are analyzed. Final candidates estimated as a lip motion image are extracted(S10). The lip motion image is determined by classifying the final candidates on a coordinate plane based on a discrimination feature of the lip motion image(S20). The final candidates positioned in a critical region of a classification standard among the classified final candidates are determined as the lip motion image based on a region separation line(S80).
Abstract translation: 提供了一种用于识别唇部运动图像的方法和装置，以使得能够在在线网络上进行标注，并实现支持向量机（Support Vector Machine，支持向量机）模式分类。 分析从成像单元接收的脸部运动图像帧。 提取作为唇部运动图像估计的最终候选（S10）。 通过基于唇部运动图像的识别特征，在坐标平面上分类最终候选来确定唇部运动图像（S20）。 在分类最终候选者中位于分类标准的关键区域的最终候选者被确定为基于区域分离线的唇部运动图像（S80）。
-
公开(公告)号：KR1020090061917A
公开(公告)日：2009-06-17
申请号：KR1020070128926
申请日：2007-12-12
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30761 , G06F17/30752 , G06F17/30769
Abstract: A method and an apparatus for providing the voice data base satisfying the requirement specification of a user are provided to provide voice database complying with for the requirement specification of the user. A first search condition for specifying voice database to be provided is received from a user computer(S10). The voice database complying with for the received first search condition is searched in a voice data base storage(S50). A voice database list including the searched voice database is transmitted to the user computer(S60). The voice data base selection signal showing the voice data base selected from the voice data base list is received from the user computer(S70). The voice data base specified with the voice data base selection signal is transmitted to the user computer(S80).
Abstract translation: 提供了一种用于提供满足用户要求规范的语音数据库的方法和装置，以提供符合用户需求规范的语音数据库。 从用户计算机接收用于指定要提供的语音数据库的第一搜索条件（S10）。 在语音数据库存储中搜索符合接收的第一搜索条件的语音数据库（S50）。 将包含搜索到的语音数据库的语音数据库列表发送到用户计算机（S60）。 从用户计算机接收到表示从语音数据库列表中选择的语音数据库的语音数据库选择信号（S70）。 用语音数据库选择信号指定的语音数据库被发送到用户计算机（S80）。
-
-
-
-
-
-
-
-
-
Search Results
257
records
(took 0.031 seconds)
