-
公开(公告)号:KR1019970056172A
公开(公告)日:1997-07-31
申请号:KR1019950049264
申请日:1995-12-13
IPC: H04L7/04
Abstract: 본 발명은 전송시스템에서 주파수가 서로 다른 클럭과 데이터간의 위상정렬장치에 관한 것으로서, 주파수가 서로 다른 2개의 클럭으로(f1,f2)부터 추출된 공약수의 주파수(fc1,fc2)는 제어신호로만 사용하여 위상을 제어하고 병렬 데이터의 재생은 입력 클럭으로(f2)재생하고, 위상경계신호를(error)샘플링하여, 그 값으로 분주기의 동작을 제어함으로써 위상을 정렬함으로써 게이트수가 많고, 주파수가 높은 주문형 반도체(ASIC)설계시 신호를 저속으로 병렬화하여 처리하는데 매우 유리한 효과를 갖는다.
-
-
公开(公告)号:KR1019900007675B1
公开(公告)日:1990-10-18
申请号:KR1019870014847
申请日:1987-12-23
IPC: H04L7/04
Abstract: The controller for synchronising the data and clock with digital elements comprises a transition detector (1) detecting the transition time, a transition signal delay circuit (2) delaying the detection signal in sequence, a data delay line (3) delaying an input data (ID) in sequency by a delay circuit (k), a dual 4:1 selector (4) providing the delayed transition and data signals one by one to output terminals (Zt,Zd), a phase detector (5) providing the counter signals (S0,S1), and a data reproduction circuit (7) providing output data (OD) from output terminal (Q5) of a flipflop (FF5).
Abstract translation: 用于使数据和时钟与数字元件同步的控制器包括检测转换时间的转换检测器(1),顺序地延迟检测信号的转移信号延迟电路(2),延迟输入数据的数据延迟线(3) ID),延迟电路(k)的顺序的双重4:1选择器(4),逐个向输出端子(Zt,Zd)提供延迟的转换和数据信号;相位检测器(5),提供计数器信号 (S0,S1)和从触发器(FF5)的输出端子(Q5)提供输出数据(OD)的数据再现电路(7)。
-
公开(公告)号:KR102223653B1
公开(公告)日:2021-03-05
申请号:KR1020160076806
申请日:2016-06-20
Applicant: 한국전자통신연구원
Abstract: 본발명의일 실시예에따른음성신호처리장치는사용자의음성신호를입력받는입력부, 상기사용자의발화에기인하는움직임을감지해서상기사용자의음성신호발화구간식별을위한보조신호를감지하는감지부, 상기사용자로부터동작모드의선택및 상기음성신호와보조신호에대한프로토콜적용방식의선택중 적어도하나에관한정보를입력받는스위치및 선택된상기동작모드가제 1 동작모드인경우상기음성신호를제 1 프로토콜을이용하여외부단말로전송하고, 선택된상기동작모드가제 2 동작모드인경우상기음성신호및 보조신호를상기제 1 프로토콜을이용하여상기외부단말로전송하거나, 상기음성신호및 보조신호별로상이하게각각상기제 1 프로토콜및 제 2 프로토콜중 하나의프로토콜을이용하여상기외부단말로전송하는신호처리부를포함할수 있다.
-
-
公开(公告)号:KR101578766B1
公开(公告)日:2015-12-22
申请号:KR1020110090283
申请日:2011-09-06
Applicant: 한국전자통신연구원
IPC: G10L15/08
Abstract: 본발명은선택적포즈가삽입될단어목록을기반으로요소 WFST를구성함으로써, 음성인식의성능을떨어뜨리지않으면서탐색공간의크기증가를최소화할수 있는음성인식용탐색공간생성장치및 방법에관한것이다.이를위하여본 발명은발음사전과, 선택적포즈가삽입될단어목록을저장하고있는단어목록데이터베이스와, 상기발음사전으로부터읽어들인각 단어의발음열을이용하여탐색공간을생성하되, 상기읽어드린단어가상기단어목록데이터베이스에포함된경우상기읽어드린단어에선택적포즈를삽입시켜탐색공간을생성하는탐색공간구현부와, 상기선택적포즈가삽입된탐색공간이저장된데이터베이스를포함하는음성인식용탐색공간생성장치를제공한다.
-
公开(公告)号:KR1020140082157A
公开(公告)日:2014-07-02
申请号:KR1020120151688
申请日:2012-12-24
Applicant: 한국전자통신연구원
Inventor: 김동현
IPC: G10L15/14
CPC classification number: G10L15/32 , G10L15/065
Abstract: Disclosed are a device and a method for speech recognition using multiple acoustic models. The device for speech recognition using multiple acoustic models according to the present invention comprises a speech data database (DB) to store speech data collected in various noise environments; a model generation means to classify the collected speech data according to speaker and environment and generate an acoustic model of a binary tree structure as a result of the classification; and a speech recognition means to extract feature data of the input speech data when the speech data is input from a user, select multiple models from the previously generated acoustic model based on the extracted feature data, recognize the speech data in parallel based on the selected multiple models, and output a word sequence corresponding to the speech data as a result of the recognition.
Abstract translation: 公开了一种使用多种声学模型进行语音识别的装置和方法。 根据本发明的使用多个声学模型的用于语音识别的装置包括:语音数据数据库(DB),用于存储收集在各种噪声环境中的语音数据; 模型生成装置,用于根据说话者和环境对所收集的语音数据进行分类,并作为分类的结果生成二叉树结构的声学模型; 以及语音识别装置,用于当从用户输入语音数据时提取输入语音数据的特征数据,基于所提取的特征数据从先前生成的声学模型中选择多个模型,基于所选择的并行识别语音数据 作为识别的结果,输出与语音数据对应的单词序列。
-
公开(公告)号:KR1020130026855A
公开(公告)日:2013-03-14
申请号:KR1020110090283
申请日:2011-09-06
Applicant: 한국전자통신연구원
IPC: G10L15/08
Abstract: PURPOSE: A search space generator for recognizing voice is provided to improve the accuracy of voice recognition by recognizing the voice by using a voice articulation database for training a voice model. CONSTITUTION: A search space generator for recognizing voice includes a pronunciation dictionary(100), a word list database(120), a WFST(Weighted Finite State Transducer) L realization unit(140), and a WFST L database(160). The WFST L implementation unit acquires a pronunciation string for each word by reading the pronunciation dictionary. The WFST L implementation unit generates WFST L in which a selective pause is inserted by comparing the acquired pronunciation dictionary with the word list stored in the word list database. [Reference numerals] (100) Pronunciation dictionary; (120) Word list database; (140) WFST L realization unit; (160) WFST L database
Abstract translation: 目的:提供用于识别语音的搜索空间发生器,以通过使用用于训练语音模型的语音发音数据库识别语音来提高语音识别的准确性。 构成:用于识别语音的搜索空间发生器包括发音字典(100),单词列表数据库(120),WFST(加权有限状态传感器)L实现单元(140)和WFST L数据库(160)。 WFST L实现单元通过读取发音字典获取每个单词的发音字符串。 WFST L实现单元产生WFST L,其中通过将获取的发音字典与存储在单词列表数据库中的单词列表进行比较来插入选择性暂停。 (附图标记)(100)发音字典; (120)词汇表数据库; (140)WFST L实现单元; (160)WFST L数据库
-
59.
公开(公告)号:KR1020130026847A
公开(公告)日:2013-03-14
申请号:KR1020110090273
申请日:2011-09-06
Applicant: 한국전자통신연구원
Inventor: 김동현
IPC: G10L15/14
Abstract: PURPOSE: A voice recognition system using an online unsupervised characteristic vector adaptation method and a method thereof are provided to offer a recognition performance by using conversion parameters which convert the characteristic vector of voice data. CONSTITUTION: A voice recognition system extracts a characteristic vector from inputted voice data(410). The voice recognition system selects a GMM(Gaussian Mixture Model) which is close to the characteristic vector through a tress search method(430). The voice recognition system calculates conversion parameters by using the selected GMM(440). The voice recognition system converts the characteristic vector by using the calculated conversion parameters(450). The voice recognition system recognizes the voice of a user(460). [Reference numerals] (410) Extracting a characteristic vector from voice data; (420) Selecting the characteristic vector as much as a window size; (430) Selecting the most similar GMM through tree searching; (440) Measuring conversion parameters; (450) Converting the characteristic vector using the conversion parameters; (460) Recognizing the voice of a user; (AA) Start; (BB) End
Abstract translation: 目的:提供使用在线无监督特征向量自适应方法及其方法的语音识别系统,通过使用转换语音数据的特征向量的转换参数来提供识别性能。 构成:语音识别系统从输入的语音数据(410)中提取特征矢量。 语音识别系统通过发声搜索方法(430)选择接近特征向量的GMM(高斯混合模型)。 语音识别系统通过使用所选择的GMM(440)来计算转换参数。 语音识别系统通过使用计算的转换参数(450)来转换特征向量。 语音识别系统识别用户的语音(460)。 (附图标记)(410)从语音数据提取特征向量; (420)选择特征向量尽可能多的窗口大小; (430)通过树形搜索选择最相似的GMM; (440)测量转换参数; (450)使用转换参数转换特征向量; (460)识别用户的声音; (AA)开始; (BB)结束
-
公开(公告)号:KR101134682B1
公开(公告)日:2012-04-09
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.
-
-
-
-
-
-
-
-
-