-
公开(公告)号：KR1020130099666A
公开(公告)日：2013-09-06
申请号：KR1020120021346
申请日：2012-02-29
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30681 , G06F17/2809 , G10L15/26
Abstract: PURPOSE: A target word generation device of a compound proper noun and a method thereof are provided to enable a user using source language and another user using target language to communicate well by effectively performing interconversion between a compound proper noun of a source language and a target word of a target language. CONSTITUTION: A target word database (DB) (10) is constructed by the combination of unit target words for compound proper nouns or by the combination of unit target words which converts the part in which target words do not exist into the literation of fixed characters. A unit target word DB (12) stores a unit target word list of compound proper nouns which are separated into a target word unit. A target word construction unit (14) constructs the target word DB and the unit target word DB; and a voice recognition unit (16) outputs voice recognition sentences for an input source language. A target word generation unit (18) generates target words based on the target word DB and the unit target word DB for the compound proper nouns which are included in the voice recognition sentences. [Reference numerals] (10) Target word database (DB); (12) Unit target word DB; (14) Target word construction unit; (16) Voice recognition unit; (18) Target word generation unit; (20) Automatic translation unit; (22) Voice composing unit; (AA) Source language vocalization; (BB) Sound composed with target languages
Abstract translation: 目的：提供一种复合专有名词及其方法的目标词生成装置，以使得用户能够使用源语言，并且使用目标语言的另一用户能够通过有效地执行源语言的复合专用词与目标之间的相互转换来良好地进行通信 目标语言的词。 构成：目标词数据库（DB）（10）由复合专有名词的单位目标词的组合或通过将不存在目标词的部分转换为固定字符的文字的单位目标词的组合构成 。 单位目标字DB（12）存储分离为目标字单元的复合专有名词的单位目标字列表。 目标词构造单元（14）构成目标字DB和单位目标字DB; 并且语音识别单元（16）输出用于输入源语言的语音识别语句。 目标字生成单元（18）基于目标字DB和包含在语音识别语句中的复合专有名词的单位目标字DB生成目标字。 （附图标记）（10）目标字数据库（DB）; （12）单位目标字DB; （14）目标字施工单位; （16）语音识别单元; （18）目标词生成单元; （20）自动翻译单位; （22）语音组合单元; （AA）来源语言发声; （BB）声音由目标语言组成
-
公开(公告)号：KR1020130042839A
公开(公告)日：2013-04-29
申请号：KR1020110106952
申请日：2011-10-19
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2827 , G06F17/30684
Abstract: PURPOSE: A similar sentence searching device and a method are provided to improve a similar sentence searching technology performance by measuring sentence similarity for a voice recognition result. CONSTITUTION: An input unit(100) inputs a random sentence. A first language processing unit(102) processes a sentence inputted through the input unit as a sentence of the first language. A first language similarity calculation unit(104) extracts a similar sentence to the sentence of the first language by referring to the translated sentence of a translation sentence database. A translation unit(106) translates a random sentence with a sentence of the second language. A second language processing unit(108) processes the second language sentence translated by the translation unit. A second language similarity calculation unit(110) extracts a similar sentence to the second language sentence by referring the set translated sentence of the translation sentence database. A ranking controlling unit(112) controls a sentence output ranking by combining the extracted combination results. [Reference numerals] (100) Input unit; (102) First language processing unit; (104) First language similarity calculation unit; (106) Translation unit; (108) Second language processing unit; (110) Second language similarity calculation unit; (112) Ranking controlling unit; (114) Output unit; (200) Translated sentence DB; (AA) Inputting a sentence;
Abstract translation: 目的：提供类似的句子搜索装置和方法，通过测量语音识别结果的句子相似度来改进类似的句子搜索技术性能。 构成：输入单元（100）输入随机句子。 第一语言处理单元（102）将通过输入单元输入的句子作为第一语言的句子进行处理。 第一语言相似度计算单元（104）通过参考翻译句子数据库的翻译句子来提取与第一语言的句子类似的句子。 翻译单元（106）将随机句子与第二语言的句子进行翻译。 第二语言处理单元（108）处理由翻译单元翻译的第二语言句子。 第二语言相似度计算单元（110）通过参考翻译句子数据库的设定的翻译句子来提取与第二语言句子类似的句子。 排名控制单元（112）通过组合所提取的组合结果来控制句子输出排名。 （附图标记）（100）输入单元; （102）第一语言处理单元; （104）第一语言相似度计算单元; （106）翻译单位; （108）第二语言处理单元; （110）第二语言相似度计算单元; （112）排名控制单位; （114）输出单元; （200）翻译句子DB; （AA）输入句子;
-
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：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）。
-
Patent Agency Ranking
公开(公告)号：KR100684160B1
公开(公告)日：2007-02-20
申请号：KR1020050119975
申请日：2005-12-08
Applicant: 한국전자통신연구원
IPC: G06F17/20
Abstract: A device and a method for analyzing a dialog with NE(Named Entity) recognition are provided to correct an error of an NE with the dialog during the dialog with a user, and solve an ambiguity problem or a new vocabulary through the dialog by performing diverse dialogs with utilization of the NE. An input part(10) inputs a text, which is a speech recognition result, or receives characters from a user. An intention analyzer(20) analyzes a user intention from the inputted text. An NE recognizer(30) checks over whether the inputted text includes a thing to be recognized by the NE. A dialog manager(40) manages the user dialog for the inputted dialog checked in the NE recognizer. A dialog output generator(50) generates an answer according to the user intention. An output part(60) outputs a result of the dialog output generator to the user.
Abstract translation: 提供一种用于分析具有NE（命名实体）识别的对话的设备和方法，以在与用户对话期间用对话来纠正NE的错误，并且通过执行多样化来通过对话解决歧义问题或新词汇 使用NE的对话框。 输入部分（10）输入作为语音识别结果的文本，或者从用户接收字符。 意图分析器（20）从输入的文本分析用户意图。 NE识别器（30）检查输入的文本是否包括要被NE识别的东西。 对话管理器（40）管理NE识别器中检查的输入对话的用户对话。 对话输出生成器（50）根据用户意图生成答案。 输出部分（60）将对话输出生成器的结果输出给用户。
-
公开(公告)号：KR100431190B1
公开(公告)日：2004-05-12
申请号：KR1020010062382
申请日：2001-10-10
Applicant: 한국전자통신연구원
IPC: G06F17/20
Abstract: PURPOSE: A part of speech tagging system and method is provided to unify a general dictionary with subject dictionaries, and to make it easy tagging words included in the subject dictionary by giving a weight value to the words included in the subject dictionary. CONSTITUTION: The system comprises a sentence input module(1), a tagging module(2), a subject classification module(3), a dictionary storage(4), the first storage(5), the second storage(6), and a tagging result output module(7). The first storage(5) stores a general dictionary, and the second storage(6) stores plural subject dictionaries. The tagging module(2) performs a procedure of tagging a part of speech on each word included in the sentence, input via the sentence input module(1), by using the dictionary storage(4) in which each word is set with a corresponding part of speech. The subject classification module(3) classifies the words included in the sentence by using the tagging result.
Abstract translation: 目的：提供一种词性标注系统和方法，用于将普通词典与主题词典统一起来，并且通过给主题词典中包括的词给出权重值来使其易于标记包含在主题词典中的词。 该系统包括句子输入模块（1），标记模块（2），主题分类模块（3），词典存储器（4），第一存储器（5），第二存储器（6）和 标记结果输出模块（7）。 第一存储器（5）存储通用词典，并且第二存储器（6）存储多个主题词典。 标注模块（2）通过使用其中每个词被设置有对应的词典存储器（4）的词典存储器（4）来执行对经由句子输入模块（1）输入的句子中包括的每个词语的词类加标签的过程 词性的一部分。 主题分类模块（3）通过使用标签结果来对包含在句子中的单词进行分类。
-
公开(公告)号：KR100381013B1
公开(公告)日：2003-04-26
申请号：KR1020000077824
申请日：2000-12-18
Applicant: 한국전자통신연구원
IPC: H04N7/08
Abstract: PURPOSE: A system and a method for inputting subtitle using a voice recognition device are provided to input subtitle in live broadcasting program through a voice recognition device and a stenographer. CONSTITUTION: A system for inputting subtitle using a voice recognition device includes a voice classification unit(120), a voice recognition unit(130), a subject classification unit(140), a subtitle inputting and correcting unit(150), and a character data transmitter(160). The voice classification unit analyzes frequency components of voice signals output from a TV voice output unit(110) to classify voices. The voice recognition unit recognizes the voice signals to extract character data and calculates the reliability of the character data. The subtitle classification unit extracts a key word using the character data to classify subjects. The subtitle inputting and correcting unit outputs the character data and its reliability, voice classification information and subject information and receives corrected information according to the output data and information to output character data. The character data transmitter receives the corrected character data and transmits the data to a broadcasting server.
Abstract translation: 目的：提供一种使用语音识别装置输入字幕的系统和方法，以通过语音识别装置和速记器在直播节目中输入字幕。 用于使用语音识别设备输入字幕的系统包括语音分类单元（120），语音识别单元（130），主题分类单元（140），字幕输入和校正单元（150）以及字符 数据发送器（160）。 语音分类单元分析从TV语音输出单元（110）输出的语音信号的频率分量以分类语音。 语音识别单元识别语音信号以提取字符数据并计算字符数据的可靠性。 字幕分类单元使用字符数据来提取关键词以分类主题。 字幕输入和校正单元输出字符数据及其可靠性，语音分类信息和对象信息，并根据输出数据和信息接收校正信息以输出字符数据。 字符数据发送器接收校正的字符数据并将数据发送到广播服务器。
-
公开(公告)号：KR1020030030374A
公开(公告)日：2003-04-18
申请号：KR1020010062382
申请日：2001-10-10
Applicant: 한국전자통신연구원
IPC: G06F17/20
Abstract: PURPOSE: A part of speech tagging system and method is provided to unify a general dictionary with subject dictionaries, and to make it easy tagging words included in the subject dictionary by giving a weight value to the words included in the subject dictionary. CONSTITUTION: The system comprises a sentence input module(1), a tagging module(2), a subject classification module(3), a dictionary storage(4), the first storage(5), the second storage(6), and a tagging result output module(7). The first storage(5) stores a general dictionary, and the second storage(6) stores plural subject dictionaries. The tagging module(2) performs a procedure of tagging a part of speech on each word included in the sentence, input via the sentence input module(1), by using the dictionary storage(4) in which each word is set with a corresponding part of speech. The subject classification module(3) classifies the words included in the sentence by using the tagging result.
Abstract translation: 目的：提供语音标签系统和方法的一部分，以将通用字典与主题词典统一，并且通过给包括在主题词典中的单词赋予权重值，使得容易地标记包含在主题词典中的单词。 构成：系统包括句子输入模块（1），标签模块（2），主题分类模块（3），字典存储器（4），第一存储器（5），第二存储器（6）和 标签结果输出模块（7）。 第一存储器（5）存储通用字典，并且第二存储器（6）存储多个对象词典。 标签模块（2）通过使用其中每个单词设置有相应的字典存储器（4）来执行通过句子输入模块（1）输入的包括在句子中的每个单词上标注一部分语音的过程， 部分讲话。 主题分类模块（3）通过使用标记结果对包含在句子中的单词进行分类。
-
公开(公告)号：KR1020170060439A
公开(公告)日：2017-06-01
申请号：KR1020150164884
申请日：2015-11-24
Applicant: 한국전자통신연구원
CPC classification number: G06F17/289 , G06F17/275 , G06F17/2854 , H04M1/7255
Abstract: 본발명은상대방과의사소통이가능한언어를자동으로확인하고선택하여자동통번역함으로써사용자편리성을향상시키기위하여, 상대방통번역장치와통신으로주고받는메시지를이용하여상대방과의사소통이가능하도록상대방을위한대상언어를다양한옵션중에서자동으로확인하고선택할수 있으며, 다국어의음성이나텍스트입력에대하여, 선택된대상언어로자동통번역을수행하여결과를음성이나화면으로제공할수 있는다국어통번역장치및 방법에관한것이다.
Abstract translation: 为了通过自动检查和选择能够与对方进行通信的语言来提高用户便利性，本发明提供了对方翻译/ 能够自动识别并选择从各种选项的目标语言，并且对于多语言的语音或文本输入中，本发明涉及一种多语言翻译和解释方法和设备，可以执行自动翻译和解释提供在语音和画面的结果在所选择的目标语言。
-
-
-
-
-
-
-
-
-
Search Results
66
records
(took 0.024 seconds)
