-
公开(公告)号：KR1020100067727A
公开(公告)日：2010-06-22
申请号：KR1020080126244
申请日：2008-12-12
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A voice recognition unit and a method thereof of a multiple search base for performing a multi-search about the input speech signal of the multiple search base are provided to improve voice recognition performance about the voice signal by using FSN(Finite State Network) mode and N-gram mode. CONSTITUTION: A speech feature extracting block(102) extracts feature data about the inputted voice signal. A language model database(108) stores the FSN language model and N-gram language model. A multi-search block(104) is parallel performed the first voice search and the second voice search. The multiple search block is created in the integration search network. The multiple search block outputs the voice recognition result according to the third voice search.
Abstract translation: 目的：提供一种用于执行关于多个搜索库的输入语音信号的多次搜索的多重搜索基的语音识别单元及其方法，以通过使用FSN（有限状态网络）来改善关于语音信号的语音识别性能， 模式和N-gram模式。 构成：语音特征提取块（102）提取关于输入的语音信号的特征数据。 语言模型数据库（108）存储FSN语言模型和N-gram语言模型。 多搜索块（104）并行执行第一语音搜索和第二语音搜索。 多个搜索块在集成搜索网络中创建。 多重搜索块根据第三语音搜索输出语音识别结果。
-
公开(公告)号：KR1020100066978A
公开(公告)日：2010-06-18
申请号：KR1020080125524
申请日：2008-12-10
Applicant: 한국전자통신연구원
IPC: G10L15/183 , G06F17/28
CPC classification number: G10L15/1815 , G10L15/183
Abstract: PURPOSE: A method and a device for voice recognition using domain ontology are provided to build a domain ontology of voice recognition target and generate voice recognition grammar applying the built domain ontology and recognize voice through the voice recognition grammar, thereby improving performance of voice recognition device. CONSTITUTION: If a voice signal is inputted through a mike, a feature extraction unit extracts specific vector of a frame unit from the voice signal(S401). A sound model unit provides voice model to a voice recognition unit through modeling the signal characteristic of the voice signal(S403). The voice recognition unit performs voice recognition through a voice model, a voice recognition dictionary(S405), and voice recognition grammar(S407)(S409).
Abstract translation: 目的：提供一种使用域本体进行语音识别的方法和装置，构建语音识别目标的领域本体，并通过语音识别语法生成应用建立的域本体并识别语音的语音识别语法，从而提高语音识别设备的性能 。 构成：如果通过麦克风输入语音信号，则特征提取单元从语音信号中提取帧单位的特定向量（S401）。 声音模型单元通过对语音信号的信号特征进行建模来向语音识别单元提供语音模型（S403）。 语音识别单元通过语音模型，语音识别字典（S405）和语音识别语法（S407）进行语音识别（S409）。
-
公开(公告)号：KR1020100062825A
公开(公告)日：2010-06-10
申请号：KR1020090026451
申请日：2009-03-27
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A voice synthesis device and a method thereof are provided, in which the parametric value of the voice section of low reliability among the composite tone of the voice recognition unit is readjusted automatically. CONSTITUTION: A text voice composition unit(200) outputs the first composite sound by the synthesis of the inputted text sentence. A voice recognition unit(202) performs the first voice recognition in the state that the neighboring noise is added to the first composite sound. The voice recognition unit readjusts the voice parameter value about the voice section where the voice recognition reliability value is lower than the fixation standard. A voice composition unit(204) outputs the second composite tone by changed voice parameter value and the recognized voice.
Abstract translation: 目的：提供一种语音合成装置及其方法，其中自动地重新调整语音识别单元的复合音调中的低可靠性的语音部分的参数值。 构成：文本语音合成单元（200）通过合成输入的文本句子来输出第一复合声音。 语音识别单元（202）在相邻噪声被添加到第一复合声音的状态下执行第一语音识别。 语音识别单元重新调整声音识别可靠性值低于固定标准的声音部分的语音参数值。 语音合成单元（204）通过改变的语音参数值和识别的语音输出第二复合音调。
-
公开(公告)号：KR1020090066067A
公开(公告)日：2009-06-23
申请号：KR1020070133677
申请日：2007-12-18
Applicant: 한국전자통신연구원
IPC: G06F17/28
CPC classification number: G06F17/2872 , G06F17/2818 , G06F17/2863
Abstract: An automatic Korean/English translating method and an apparatus thereof including an automatic pattern base translating technique are provided to generate final translating result by accurately dividing a Korean sentence. A result of A morphological analysis and a phrase analysis are cut by two or more partial original sentences(S208). A pattern machine half machine translation bilingual document and a statistical machine translation translated sentence are generated based on the divided result(S210, S212). A partial translated sentence about the Korean original sentence is synthesized to one English sentence by using translation result(S218).
Abstract translation: 提供了一种自动的韩文/英文翻译方法及其包括自动图案基本翻译技术的装置，以通过精确地划分韩语句子来产生最终的翻译结果。 A形态分析和短语分析的结果被两个或多个部分原始句子切割（S208）。 基于分割结果生成模式机半机翻译双语文档和统计机器翻译翻译句子（S210，S212）。 通过使用翻译结果将关于韩语原始句子的部分翻译句子合成为一个英文句子（S218）。
-
公开(公告)号：KR1020080073396A
公开(公告)日：2008-08-11
申请号：KR1020070011940
申请日：2007-02-06
IPC: H04N19/30 , H04N21/63 , H04N21/236
CPC classification number: H04N19/30 , H04N19/70 , H04N21/234327 , H04N21/23605 , H04N21/2362 , H04N21/2365 , H04N21/242 , H04N21/631
Abstract: A scalable coding apparatus and method are provided to divide a video signal into the video signal of a base layer and the video signal of an enhancement layer and encode the video signal using an MPEG4 SVC method and multiplex the video signal by layer, thereby enabling a receiver to receive video encoding data by layer selectively according to the performance of the receiver. A video encoding unit(10) receives a video signal and performs SVC(Scalable Video Coding) in an MPEG4(Moving Picture Experts Group4) SVC method to output the video encoding data of a base layer and the video encoding data of an enhancement layer. An audio encoding unit(20) receives an audio signal and performs audio encoding in an MPEG4 audio encoding method to output the audio encoding data of the base layer and outputs the audio encoding data of the enhancement layer selectively. A base layer multiplexing unit(30) performs SL(Sync Layer) packetizing, PES(Packetized Elementary Stream) packetizing, section generation, and TS(Transport Stream) multiplexing in the video encoding data of the base layer. An enhancement layer multiplexing unit(40) performs SL packetizing, PES packetizing, section generation, and TS multiplexing in the video encoding data of the enhancement layer.
Abstract translation: 提供了一种可分级编码装置和方法，用于将视频信号划分为基本层的视频信号和增强层的视频信号，并使用MPEG4 SVC方法对视频信号进行编码，并逐层复用视频信号， 接收机根据接收机的性能选择性地接收视频编码数据。 视频编码单元（10）接收视频信号并在MPEG4（运动图像专家组4）SVC方法中执行SVC（可缩放视频编码），以输出基本层的视频编码数据和增强层的视频编码数据。 音频编码单元（20）接收音频信号并以MPEG4音频编码方法执行音频编码，以输出基本层的音频编码数据，并选择性地输出增强层的音频编码数据。 基层复用单元（30）在基层的视频编码数据中执行SL（Sync Layer）打包，PES（Packetized Elementary Stream）分组，部分生成和TS（传输流）复用。 增强层复用单元（40）在增强层的视频编码数据中执行SL分组，PES分组，部分生成和TS复用。
-
Patent Agency Ranking
公开(公告)号：KR100805190B1
公开(公告)日：2008-02-21
申请号：KR1020060086139
申请日：2006-09-07
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2775 , G06F17/2735 , G06F17/289
Abstract: A device and a method for segmenting an English sentence are provided to improve translation accuracy of machine translation and build a full text database from a simple English raw corpus for the machine translation for an English patent document. An input processor(100) segments paragraphs from an inputted English patent document. A token segmentation part(200) segments each word included in the paragraph into a token and sets a type of the token. A sentence segmentation part(300) segments a patent sentence by using the segmented token and the token type as input for an abbreviation database(610) and a proper noun database(620). A sentence segmentation knowledge builder(700) builds the abbreviation database and the proper noun database from a patent document raw corpus automatically. A sentence transformer(400) transforms an asyntactic patent sentence segmented in the sentence segmentation part by using a sentence transformation rule database(630). An output processor(500) outputs the segmented and transformed patent sentence as a result.
Abstract translation: 提供了一种用于分割英文句子的装置和方法，以提高机器翻译的翻译准确性，并从英文专利文献的机器翻译简单的英文原始语料库构建全文数据库。 输入处理器（100）从输入的英文专利文献中段落段落。 令牌分段部分（200）将段落中包括的每个单词分成令牌并设置令牌的类型。 句子分割部分（300）通过使用分割令牌和令牌类型作为缩写数据库（610）和专有名词数据库（620）的输入来分割专利句子。 句子分段知识构建器（700）自动从专利文献原始语料库构建缩写数据库和专有名词数据库。 句子变换器（400）通过使用句子转换规则数据库（630）来转换分段在句子分割部分中的合成专利句。 输出处理器（500）作为结果输出分段和转换的专利句子。
-
117.发明授权
公开(公告)号：KR100792203B1
公开(公告)日：2008-01-08
申请号：KR1020060056184
申请日：2006-06-22
Applicant: 한국전자통신연구원
Abstract: 본 발명은 본 발명은 한국어를 원문으로 하는 특허 문서에서 빈번히 등장하는 전문용어의 대역어 선정을 위해 구축되는 대역어 사전의 정보를 자동으로 생성하여 제시함으로써 수동으로 구축되던 대역어 사전의 구축 작업을 반자동화하여 대역어 사전 구축의 효율성을 높이기 위한 장치 및 방법에 관한 것으로, 특허문서에서 전문용어를 구성하는 단위 명사 및 접사의 대역어 정보를 이용하여 복합명사형 전문용어 대상 엔트리와 대역어를 추출하는 단계와, 상기 추출된 복합명사형 전문용어 대상 엔트리 및 대역어에서 미등록 단일명사 전문용어의 대역어 후보자를 선정하는 단계와, 상기 대역어 후보자가 없는 경우에 수동 구축을 위해 해당 전문용어의 예문을 추출하여 제시하는 단계를 포함하여 이루어지는데 있다.
자동번역, 전문용어 추출, 특허 문서 번역, 대역어 선정-
公开(公告)号：KR1020070061182A
公开(公告)日：2007-06-13
申请号：KR1020060056201
申请日：2006-06-22
Applicant: 한국전자통신연구원
IPC: G10L15/14 , G10L15/08 , G10L15/06 , G10L15/197
Abstract: A statistical HMM(Hidden Markov Model) part-of-speech tagging apparatus and method capable of being applied to a new domain without a tagged domain corpus are provided to select a lexicon with lexical probability varied according to a domain to which the lexicon is applied, and update the lexical probability according to the domain to improve tagging accuracy without having a tagged domain corpus in a specific domain. Tagging probability information is learnt from a previously tagged corpus to construct a lexical/part-of-speech/contextual probability information database and a lexical probability information database(S210). The lexical probability information database is domain-dependently leant and updated based on a raw corpus of an application domain(S220). Morpheme analysis is performed on an input sentence on the basis of a morpheme analysis dictionary database(S240). Statistical part-of-speech tagging is carried out on the morpheme analysis result based on the lexical/part-of-speech/contextual probability information database and the updated lexical probability information database(S250). An error in the tagging result is corrected according to a tagging error correction rule database(S260).
Abstract translation: 提供能够应用于没有标记域语料库的新领域的统计HMM（隐马尔可夫模型）语音标签装置和方法，以选择具有根据应用于词汇的域的词汇概率变化的词典 ，并根据域更新词汇概率，以提高标记准确性，而不需要在特定域中加上标记的域语料库。 从先前标记的语料库学习标记概率信息，以构建词汇/词性/语境概率信息数据库和词汇概率信息数据库（S210）。 词汇概率信息数据库基于应用领域的原始语料库进行域依赖性的更新（S220）。 基于语素分析词典数据库对输入句子进行语素分析（S240）。 基于词汇/语音/语境概率信息数据库和更新的词汇概率信息数据库，对语素分析结果进行统计词性标注（S250）。 根据标签纠错规则数据库来校正标记结果中的错误（S260）。
-
119.发明公开
公开(公告)号：KR1020070061008A
公开(公告)日：2007-06-13
申请号：KR1020060030127
申请日：2006-04-03
Applicant: 한국전자통신연구원
IPC: G06F17/30
CPC classification number: G06F17/2715 , G06F17/271
Abstract: A method and a device for automatically generating a compound noun translation using translation co-occurrence/probability information of a translation dictionary are provided to solve semantic disambiguation and synonymous translations by automatically extracting the translation co-occurrence/probability information from the dictionary and selecting the translation based on the extracted information. A translation co-occurrence and probability information extractor(107,108) respectively extracts the translation co-occurrence and probability information from the translation database(106). A compound noun extractor(102) extracts and dissolves the compound noun into words of a noun unit. A context-based translation selector(103) selects the highest context probability translation for each word based on the translation co-occurrence information. A probability-based translation selector(104) selects the highest probability translation for each word based on the translation probability information. A compound noun translation generator(105) generates the translation of the extracted compound noun by combining the selected translations.
Abstract translation: 提供一种使用翻译词典的翻译同现/概率信息自动生成复合名词翻译的方法和装置，以通过自动从词典提取翻译同现/概率信息来选择语义消歧和同义翻译 基于提取的信息进行翻译。 翻译同现和概率信息提取器（107,108）分别从翻译数据库（106）提取翻译同现和概率信息。 复合名词提取器（102）将化合物名词提取并溶解成名词单位的单词。 基于上下文的翻译选择器（103）基于翻译同现信息为每个单词选择最高的上下文概率翻译。 基于概率的翻译选择器（104）基于翻译概率信息来选择每个单词的最高概率翻译。 复合名词翻译生成器（105）通过组合所选择的翻译来生成提取的复合名词的翻译。
-
公开(公告)号：KR100617317B1
公开(公告)日：2006-08-30
申请号：KR1020050013906
申请日：2005-02-19
Applicant: 한국전자통신연구원
IPC: G06F17/20
Abstract: 본 발명에 의한 복합 명사 전문용어 사전 엔트리의 재분석 방법 및 그 장치는 전문용어 사전에서 단일 명사 전문용어와 복합 명사 전문용어를 분리하는 단계; 상기 복합 명사 전문용어에 소정의 품사를 가지는 단어를 부착하여 부분 문장을 생성하는 단계; 상기 단일명사 전문용어와 형태소 분석 기본 사전을 기초로 상기 부분문장의 형태소를 분석하는 단계; 및 상기 분석결과 상기 부분생성된 문장이 단일 명사 이외의 품사로 해석될 가능성의 유무로 상기 복합 명사의 등록 여부를 결정하는 단계;를 포함하는 것을 특징으로 하며, 형태소 분석 사전에 등재가 요구되는 복합 명사 전문용어 엔트리를 재분석하여 복합 명사 전문용어 삭제에 따른 분석 모호성 발생을 판단하고, 이에 따른 분석 사전 등재 대상 전문용어 엔트리를 선정하여 대용량 전문용어에 의해 크기가 커지는 분석 사전의 크기를 효과적으로 축소하면서 분석 정확률은 유지할 수 있는 시스템 효율성을 향상시키는 효과를 가져올 수 있다.
-
-
-
-
-
-
-
-
-
Search Results
434
records
(took 0.026 seconds)
