-
公开(公告)号：KR1020100073161A
公开(公告)日：2010-07-01
申请号：KR1020080131755
申请日：2008-12-22
Applicant: 한국전자통신연구원
CPC classification number: G10L15/187 , G10L15/10
Abstract: PURPOSE: An utterance verification method and device for isolated word an NBEST recognition result are provided to enable more reliable voice recognition by displaying the acceptance/refusal or decision failure of voice recognition by measuring inter-phoneme similarity through DTW(Dynamic Time Warping). CONSTITUTION: A pre-processing unit(104) performs feature extraction and end point detection for detecting voice section and noise processing section. An NBEST voice recognition unit(106) perform an NBEST voice recognition through a viterbi speech in consideration of a context-subordinate sound model(26). An NBEST speech verification unit(108) compares the result of an SVM(Support Vector Machine) with the similarity result to measure the similarity of voice recognition result. Therefore, the NBEST speech verification unit displays the acceptance, refusal and decision failure for the voice recognition result.
Abstract translation: 目的：提供一种用于隔离词的话语验证方法和设备，其包括NBEST识别结果，以通过通过DTW（动态时间扭曲）测量语音间相似度来显示语音识别的接受/拒绝或决策失败来实现更可靠的语音识别。 构成：预处理单元（104）执行用于检测语音段和噪声处理部分的特征提取和终点检测。 考虑到上下文从属声音模型（26），NBEST语音识别单元（106）通过维特比语音执行NBEST语音识别。 NBEST语音验证单元（108）将SVM（支持向量机）的结果与相似度结果进行比较，以测量语音识别结果的相似度。 因此，NBEST语音验证单元显示语音识别结果的接受，拒绝和决策失败。
-
公开(公告)号：KR1020100072746A
公开(公告)日：2010-07-01
申请号：KR1020080131238
申请日：2008-12-22
Applicant: 한국전자통신연구원
IPC: G10L15/20 , G10L21/0208 , G10L21/0272
Abstract: PURPOSE: A method and an apparatus for reducing a multi channel noise are provided to selectively apply beam-forming method and sound source separating method according to environment condition among multi-channel noises processing based on multi-channel voice recognition environment thereby maximizing noise processing performance. CONSTITUTION: A noise environment monitoring unit(210) grasps the number of sound source and background sound source and relative location information of user voice. According to how many information of the sound source and the relative location information of the background sound source and the user voice, a multi-channel noise processor(220) selects multi-channel noise processing methods among a plurality of multi-channel noises processing modes. The multi-channel noise processor performs noises processing by selected multi-channel noise processing method.
Abstract translation: 目的：提供一种降低多通道噪声的方法和装置，以便根据多声道噪声处理，根据环境条件选择性地应用波束形成方法和声源分离方法，从而使噪声处理性能最大化 。 构成：噪声环境监测单元（210）掌握用户声音的声源和背景声源的数量和相对位置信息。 根据声源的多少信息和背景声源和用户声音的相对位置信息，多声道噪声处理器（220）在多个多声道噪声处理模式中选择多声道噪声处理方法 。 多声道噪声处理器通过选择的多声道噪声处理方法进行噪声处理。
-
公开(公告)号：KR1020100072731A
公开(公告)日：2010-07-01
申请号：KR1020080131221
申请日：2008-12-22
Applicant: 한국전자통신연구원
CPC classification number: G01C21/3608 , G01C21/3611 , G01C21/3679 , G10L15/26
Abstract: PURPOSE: An apparatus for generating keyword for speech recognition for a navigation device is provided to enable a retrieval service of POI through voice by automatically producing the allomorph of POI which a user can say to a navigation device. CONSTITUTION: An apparatus for generating keyword for speech recognition in navigation device comprises a statistical model studying unit(202) and an allomorph generating unit. The statistical model studying unit analyzes the POI character strings. The statistical model studying unit builds probability value as statistical information. The allomorph generating unit creates the allomorphs on POI name using the statistical information.
Abstract translation: 目的：提供一种用于为导航装置生成用于语音识别的关键词的装置，以通过自动产生用户可以对导航装置说的POI的变体，从而通过语音实现POI的检索服务。 构成：用于在导航装置中生成用于语音识别的关键词的装置，包括统计模型研究单元（202）和变形生成单元。 统计模型研究单位分析POI字符串。 统计模型研究单位建立概率值作为统计信息。 变异生成单元使用统计信息在POI名称上创建变形。
-
公开(公告)号：KR1020100066916A
公开(公告)日：2010-06-18
申请号：KR1020080125433
申请日：2008-12-10
Applicant: 한국전자통신연구원
IPC: G10L99/00
Abstract: PURPOSE: A method for separating noise from an audio signal is provided to increase performance of sound source separation and increase convergence speed in a weighted learning stage, thereby increasing calculation efficiency. CONSTITUTION: A plurality of microphones records an audio signal that a user speaks and a noise signal. A beam former(20) performs a beam forming process and a blind processing separation procedure for the recorded audio signal and noise signal. The beam former spatially and statistically divides the audio signal and the noise signal. A sound source separator(30) separates the sound source signal and outputs the separated sound source signal.
Abstract translation: 目的：提供一种从音频信号中分离噪声的方法，以增加声源分离的性能，增加加权学习阶段的收敛速度，从而提高计算效率。 构成：多个麦克风记录用户说话的音频信号和噪声信号。 波束成形器（20）对记录的音频信号和噪声信号执行波束形成处理和盲目处理分离程序。 波束形成器在空间和统计学上划分音频信号和噪声信号。 声源分离器（30）分离声源信号并输出分离的声源信号。
-
公开(公告)号：KR1020100026187A
公开(公告)日：2010-03-10
申请号：KR1020080085095
申请日：2008-08-29
Applicant: 한국전자통신연구원
IPC: G10L15/08 , G10L15/26 , H04N21/438
Abstract: PURPOSE: A voice recognition information generation device, a method thereof, and a broadcast service method thereof are provided to generate a database from allomorph character string, thereby offering a broadcast service according to voice recognition. CONSTITUTION: A voice recognition information generation device includes a prior matching unit(302), a section boundary partition unit(308), a normalization unit(310), and an allomorph generation unit(312). The prior matching unit performs prior matching according to character string information of broadcast data. The section boundary partition unit partitions the section boundary of a character string of which prior matching is performed in order to generate voice recognition target character string data. The normalization unit normalizes generated voice recognition target character string. The allomorph generation unit generates allomorph character string data from normalized voice recognition target character string data.
Abstract translation: 目的：提供一种语音识别信息生成装置，其方法和广播服务方法，以从变形字符串生成数据库，从而根据语音识别提供广播服务。 构成：语音识别信息生成装置包括先验匹配单元（302），区间边界分割单元（308），归一化单元（310）和变形函数生成单元（312）。 先前的匹配单元根据广播数据的字符串信息执行先前的匹配。 区段边界分割单元对执行了先前匹配的字符串的区域边界进行分割，以便生成语音识别目标字符串数据。 归一化单元对生成的语音识别目标字符串进行归一化。 变形生成单元从归一化的语音识别目标字符串数据生成变形字符串数据。
-
Patent Agency Ranking
公开(公告)号：KR100918842B1
公开(公告)日：2009-09-28
申请号：KR1020070130721
申请日：2007-12-14
Applicant: 한국전자통신연구원
Abstract: 본 발명에 따른 대용어 참조해결 방법은, 입력된 문자열을 분석하여 문자열에 포함된 대용어를 인식하는 대용어 인식단계; 대용어의 전체의미를 분석하는 의미 분석 단계; 문자열을 청킹(chunking)한 뒤 각각의 청크에 하나의 개념을 배정하고, 개념과 전체의미를 비교분석하여 대용어가 가리킬 수 있는 대상 후보들을 선정하는 대상 후보 선정단계; 대상 후보들을 순위화(ranking)하여 대용어 복원에 사용될 참조 대상을 선정하고, 참조 대상을 이용하여 대용어를 복원하는 대용어 복원단계를 포함한다. 이와 같은 구성에 의하여, 자연어 문장의 이해가 필요한 다양한 응용분야에서 효과적으로 활용될 수 있으며 길고 복잡한 문장에서 높은 정확도로 대용어를 복원할 수 있는데 그 효과가 있다.
-
公开(公告)号：KR100908445B1
公开(公告)日：2009-07-21
申请号：KR1020070066452
申请日：2007-07-03
Applicant: 한국전자통신연구원
Abstract: 본 발명은 응답 문장 생성 장치 및 방법에 관한 것으로, 음성 인식된 문장에 대한 정확한 키 워드를 추출하여 응답 문장을 생성하는 장치 및 방법을 제공하는 데 있다. 이를 위하여, 본 발명에 따른 응답 문장 생성 방법은, 음성 인식된 문장을 형태소 분석하는 단계; 상기 문장으로부터 1차 개념열 추출을 수행하는 단계; 상기 추출된 1차 개념열을 기반으로 상기 문장에 대한 1차 의미 분석을 수행하는 단계; 상기 1차 개념열 추출 단계에서 추출되지 않은 개념열을 더 추출하기 위하여, 상기 1차 의미 분석 결과를 기반으로 상기 문장으로부터 상기 1차 개념열을 포함하는 2차 개념열 추출을 수행하는 단계; 상기 추출된 2차 개념열을 기반으로 상기 문장에 대하여 2차 의미 분석을 수행함으로써 상기 음성 인식된 문장에 대한 의미 분석 결과를 생성하는 단계; 및 상기 생성된 의미 분석 결과를 기반으로 상기 음성 인식된 문장에 대한 응답 문장을 생성하는 단계를 포함한다. 즉 음성 인식된 문장에 대하여 2차 개념열/대용어 추출 및 2차 의미 분석을 수행함으로써 음성 인식된 문장에 대하여 정확한 의미 분석을 할 수 있는 이점이 있다.
응답 문장, 의미 분석Abstract translation: 提供一种用于产生响应句子的设备和方法，以通过对语音识别语句执行第二句子/替代提取和第二含义分析来执行对语音识别句子的精确含义分析。 一种响应语句生成方法，包括以下步骤：对语音识别语句进行语素分析（200,210）; 从句子（220）中提取第一句子句子; 基于提取的第一句子句子执行句子的第一含义分析（230）; 为了进一步提取在上述第二步骤（240）中未提取的句子的点，基于第一含义分析结果从句子中提取包括第一句子句子的第二句子句子; 通过基于所提取的第二句子句子（250）执行句子的第二含义分析来生成所述语音识别句子的含义分析结果; 并且基于所生成的含义分析结果（260）来生成对语音识别语句的响应句子。
-
公开(公告)号：KR1020090061525A
公开(公告)日：2009-06-16
申请号：KR1020070128556
申请日：2007-12-11
Applicant: 한국전자통신연구원
IPC: G06F17/21
CPC classification number: G06F17/2247 , G06F17/218 , G06F17/272 , G06N5/025
Abstract: A method for extracting the structural information of a web document and a system thereof are provided to extract the attributes of a corresponding web site automatically although the learning is performed by tagging a small amount of data in the web site. By learning a web document, in which attributes are manually tagged and which is collected from a web site to be extracted, an attribute learning processing device(100) generates a studying model. An attribute extraction processing device(200) extracts attributes from an original web document. A boundary recognition studying model database(300) provides a database of a boundary recognition studying model among the studying models to the attribute extraction processing device. An attribute recognition studying model database(302) provides a database of the attribute recognition studying model among the studying models to the attribute extraction processing device.
Abstract translation: 提供用于提取web文档的结构信息的方法及其系统，以自动提取相应网站的属性，尽管通过在网站中标记少量数据来执行学习。 属性学习处理装置（100）通过学习一种web文档，其中属性被手动标记，并且从被提取的网站中收集属性，生成学习模型。 属性提取处理装置（200）从原始web文档中提取属性。 边界识别研究模型数据库（300）为属性提取处理装置的学习模型提供了边界识别学习模型的数据库。 属性识别研究模型数据库（302）在属性提取处理装置的研究模型中提供属性识别研究模型的数据库。
-
公开(公告)号：KR1020090028908A
公开(公告)日：2009-03-20
申请号：KR1020070094047
申请日：2007-09-17
Applicant: 한국전자통신연구원
Abstract: A voice conversation analysis system and a method thereof are provided to obtain the high accuracy and fast processing speed by restoring the abbreviation and substitute based on the general dialogue analysis. A character string and voice signal are inputted to a user input unit(100) from a user. A voice recognition circuit(110) analyzes the voice signal which is inputted from the user input unit, and then converts the analyzed voice signal into a character string having the same content. Data outputted from the voice recognition circuit are inputted to a language analysis part(120), and then performs the morpheme analysis, speech act analysis and concept recognition by referring to data of a storage unit(160).
Abstract translation: 提供语音会话分析系统及其方法，以通过基于一般对话分析恢复缩写和替换来获得高精度和快速的处理速度。 字符串和语音信号从用户输入到用户输入单元（100）。 语音识别电路（110）分析从用户输入单元输入的语音信号，然后将所分析的语音信号转换成具有相同内容的字符串。 从语音识别电路输出的数据被输入到语言分析部（120），然后参照存储部（160）的数据进行语素分析，语音动作分析，概念识别。
-
公开(公告)号：KR1020080052279A
公开(公告)日：2008-06-11
申请号：KR1020070074287
申请日：2007-07-25
Applicant: 한국전자통신연구원
IPC: H04N21/43 , H04N21/2343
Abstract: An interactive TV agency service method for providing real-life information and an apparatus therefor are provided to acquire real-life information updated on a web in real time and expand the acquired information to various region when necessary by performing operation for which a user wishes through an interactive interface including a voice, a remote controller, and a text input and providing a corresponding suitable response. A dialogue sentence analyzing unit(20) analyzes an input sentence received from a user. A dialogue management unit(30) analyzes the request of the user by using the analyzed result of the dialogue sentence analyzing unit. When a real-time information update is requested from the dialogue management unit, a real-time automatic knowledge constructing unit(70) extracts daily life information updated on a web in real time and stores the extracted information in a daily information database. A response generating unit(40) generates a response for the request of the user analyzed in the dialogue management unit and provides the response to the user. When it is impossible to respond to the request of the user or an error is generated in the response for the request of the user, an exception processing unit(80) recovers a system to allow the user to cancel the request of the user.
Abstract translation: 提供用于提供现实生活信息的交互式电视机构服务方法及其装置，用于获取在网络上实时更新的现实生活信息，并且在必要时通过执行用户期望的操作将获取的信息扩展到各个区域 包括语音，遥控器和文本输入的交互式界面，并提供对应的合适响应。 对话句分析单元（20）分析从用户接收的输入语句。 对话管理单元（30）通过使用对话句分析单元的分析结果来分析用户的请求。 当从对话管理单元请求实时信息更新时，实时自动知识构建单元（70）实时地提取在web上更新的日常生活信息，并将提取的信息存储在日常信息数据库中。 响应生成单元（40）生成对话管理单元中分析的用户的请求的响应，并向用户提供响应。 当不可能响应于用户的请求或在针对用户的请求的响应中产生错误时，异常处理单元（80）恢复系统以允许用户取消用户的请求。
-
-
-
-
-
-
-
-
-
Search Results
128
records
(took 0.03 seconds)
