公开(公告)号：KR1020130067854A

公开(公告)日：2013-06-25

申请号：KR1020110134848

申请日：2011-12-14

Applicant: 한국전자통신연구원

Inventor： 전형배 ,  정의석 ,  정호영 ,  이윤근

IPC: G06F17/20 ,  G06F17/40

CPC classification number: G06F17/277 ,  G06F17/18

Abstract: PURPOSE: A Corpus-based language model discrimination learning method and a device thereof are provided to easily build and use a learning database corresponding to a target domain by building a discrimination learning training corpus database with a text corpus. CONSTITUTION: A language model discrimination learning database extracts a voice feature vector from a corpus database to be built(S302). Continuous speech voice recognition is performed by receiving the voice feature vector(S303). The language model discrimination learning is performed by using a score sentence score and a voice recognition result outputted through continuous speech voice recognition performance(S304). A discrimination language model is generated(S305). [Reference numerals] (AA) Start; (BB) End; (S301) Build a DB for language model discrimination learning; (S302) Extract a voice feature vector; (S303) Recognize voice of continuous speech; (S304) Perform the language model discrimination learning; (S305) Generate a discriminative language model

Abstract translation: 目的：提供一种基于语料库的语言模型识别学习方法及其设备，通过建立具有文本语料库的歧视学习训练语料库数据库，轻松构建和使用与目标域对应的学习数据库。 构成：语言模型识别学习数据库从要构建的语料库数据库中提取语音特征向量（S302）。 通过接收语音特征向量来执行连续语音识别（S303）。 通过使用通过连续语音识别性能输出的分数句分数和语音识别结果来执行语言模型识别学习（S304）。 生成辨别语言模型（S305）。 （附图标记）（AA）开始; （BB）结束; （S301）建立语言模型歧视学习DB; （S302）提取语音特征向量; （S303）识别连续语音的声音; （S304）执行语言模型识别学习; （S305）生成歧视语言模型

公开(公告)号：KR1020130011574A

公开(公告)日：2013-01-30

申请号：KR1020110072813

申请日：2011-07-22

Applicant: 한국전자통신연구원

Inventor： 정의석 ,  이윤근 ,  송화전 ,  전형배 ,  정호영

IPC: G10L15/16

Abstract: PURPOSE: A confusion network rescoring device for Korean continuous voice recognition, a method for generating a confusion network by using the same, and a rescoring method thereof are provided to improve a generation speed of the confusion network by setting a limit of a lattice link probability in a process for converting a lattice structure into a confusion network structure. CONSTITUTION: A confusion network rescoring device receives on or more lattices generated through voice recognition(S105). The device calculates each posterior probability of the lattices(S110). The device allocates a node included in the lattices to plural equivalence classes based on the posterior probability(S120,S130,S135). The device generates a confusion set by using the equivalence classes(S150,S155). The device generates a confusion network based on the confusion set. [Reference numerals] (AA) Start; (BB,DD,FF,HH,JJ) No; (CC,EE,GG,II,KK) Yes; (LL) End; (S105) Inputting lattices through voice recognition; (S110) Calculating each posterior probability of the lattices; (S115) Inputting SLF?; (S120) Allocating a first node(no) of the lattices to a first equivalence class(NO); (S125) N_i and n_i links exist?; (S130) Allocating an i-th node(n_i) of the lattices to a j-th equivalence class(N_j); (S135) Allocating the i-th node(n_i) of the lattices to a i-th equivalence class(N_i); (S140) Allocating all nodes of the lattices?; (S145) If u∈N_s n_i∈N_t, t=s+1 in e(u->n_i); (S150) Classifying the e(u->n_i) as CS(N_s,N_t); (S155) Classifying the e(u->n_i) as CS(N_k,N_k+1); (S160) Normalizing link probability in an extracted CS sequence; (S165) Adding a Null link, and allocating remaining probability values of a normalized value; (S170) Possibility value of the Null link > possibility value of the other link; (S175) Excluding the CS sequence from a voice recognition result

Abstract translation: 目的：提供一种用于韩语连续语音识别的混淆网络解密设备，通过使用该方法产生混淆网络的方法及其解决方法，以通过设置网格链路概率的限制来提高混淆网络的生成速度 在将网格结构转换成混淆网络结构的过程中。 构成：混淆网络重新获取装置接收通过语音识别产生的或多个格子（S105）。 该装置计算格子的每个后验概率（S110）。 该设备基于后验概率将包括在格子中的节点分配给多个等价类（S120，S130，S135）。 该设备通过使用等价类产生混淆集（S150，S155）。 该设备基于混淆集产生混淆网络。 （附图标记）（AA）开始; （BB，DD，FF，HH，JJ）否; （CC，EE，GG，II，KK）是; （LL）结束; （S105）通过语音识别输入格子; （S110）计算格子的每个后验概率; （S115）输入SLF？ （S120）将格子的第一节点（否）分配给第一等价类（NO）; （S125）存在N_i和n_i个链路？ （S130）将格子的第i个节点（n_i）分配给第j个等价类（N_j）; （S135）将格子的第i个节点（n_i）分配给第i个等价类（N_i）; （S140）分配格子的所有节点？ （S145）如果u∈N_sn_i∈N_t，则e（u-> n_i）中的t = s + 1; （S150）将e（u-> n_i）分类为CS（N_s，N_t）; （S155）将e（u-> n_i）分为CS（N_k，N_k + 1）; （S160）在提取的CS序列中归一化链路概率; （S165）添加空链路，分配归一化值的剩余概率值; （S170）空链路的可能值>其他链路的可能值; （S175）从语音识别结果中排除CS序列

公开(公告)号：KR1020120043552A

公开(公告)日：2012-05-04

申请号：KR1020100104894

申请日：2010-10-26

Applicant: 한국전자통신연구원

Inventor： 박전규 ,  정훈 ,  전형배 ,  정의석 ,  김종진 ,  정호영 ,  강병옥 ,  강점자 ,  박기영 ,  이성주 ,  이윤근 ,  송화전

IPC: G10L15/14

Abstract: PURPOSE: A voice recognition apparatus and a method thereof are provided to increase recognition speed of an input signal and to perform recognition of an input signal in parallel. CONSTITUTION: A global database unit(10) includes a global feature vector(12), a global vocabulary model(14), and a global sound model(16). A recognition unit(20) includes separated recognition units(22a~22n). A plurality of separate recognition units performs voice recognition in parallel. A separate database unit(30) includes separate language models. A collection and evaluation unit(40) collects and evaluates the recognition result of the separate recognition unit.

Abstract translation: 目的：提供一种语音识别装置及其方法，以增加输入信号的识别速度并且并行执行输入信号的识别。 构成：全局数据库单元（10）包括全局特征向量（12），全球词汇模型（14）和全局声音模型（16）。 识别单元（20）包括分离的识别单元（22a〜22n）。 多个单独的识别单元并行执行语音识别。 单独的数据库单元（30）包括单独的语言模型。 收集和评估单元（40）收集并评估单独识别单元的识别结果。

公开(公告)号：KR101082025B1

公开(公告)日：2011-11-10

申请号：KR1020090070274

申请日：2009-07-30

Applicant: 한국전자통신연구원 ,  한국과학기술원

Inventor： 정의석 ,  유제훈 ,  김병휘 ,  고재상 ,  설동민 ,  박홍식 ,  류미선 ,  박지용

IPC: H04L12/22 ,  H04L12/24 ,  H04B10/032 ,  H04B10/25

Abstract: 상이한보호복구요구를갖는사용자들이연결되는대상망의보호복구방법에관한것으로, 사용자별가용도정보와대상망의특성을반영하는파라미터들을포함하는망 구성요소들을분석하고, 분석결과에기초하여, 최적화된대상망의보호복구구조를결정하는대상망의보호복구방법에의해가입자유형에따라요구하는보호복구요구정도가다른경우에도망의장애가발생했을때, 이를해결하여망 기능을신속하게회복할수 있는효과가있다.

公开(公告)号：KR101078055B1

公开(公告)日：2011-10-31

申请号：KR1020090026653

申请日：2009-03-27

Applicant: 한국전자통신연구원

Inventor： 설동민 ,  정의석 ,  유제훈 ,  김병휘

IPC: H04B10/03 ,  H04B10/2581 ,  H04B10/275

Abstract: 본발명은환형수동형광 가입자망에서의보호복구절체장치에관한것이다. 본발명에따른광선로종단장치의하향신호가수동소자로이루어진다수의원격노드(RN)에송신되도록스위칭하는하향신호스위치와, 다수의원격노드들의상향신호가광선로종단장치에수신되도록스위칭하는상향신호스위치와, 광선로종단장치의하향신호또는다수의원격노드들의상향신호를송수신하는광신호송수신부와, 광신호송수신부를통해수신된다수의원격노드들의상향신호를상향신호스위치를통해광선로종단장치에전송하되, 수신된상향신호를분석하여장애가감지되면, 장애가감지된구간의광선로를우회하여다수의원격노드들에하향신호가전송되도록하향신호스위치를동작시키는제어부를포함하는것을특징으로한다. 또한, 본발명에따른광선로종단장치의상향신호스위치또는하향신호스위치는광 스위치또는전기스위치인것을특징으로한다.

公开(公告)号：KR101072886B1

公开(公告)日：2011-10-17

申请号：KR1020080127707

申请日：2008-12-16

Applicant: 한국전자통신연구원

Inventor： 전형배 ,  정호영 ,  박전규 ,  정훈 ,  이윤근 ,  강점자 ,  정의석 ,  강병옥 ,  김종진 ,  왕지현 ,  이성주 ,  박기영

IPC: G10L25/78 ,  G10L25/24 ,  G10L15/14 ,  G10L15/20

Abstract: 본발명은캡스트럼평균차감방법및 그장치에관한것으로, 온라인음성인식서비스에서묵음구간의캡스트럼평균값을사용하여실제음성구간전체의캡스트럼평균값을추정함으로써, 채널특성을보다정확하게정규화할수 있다. 또한, 본발명은주변환경변화가발생하는경우에대해서도정확한캡스트럼평균값을추정할수 있어채널정규화성능이우수하다. 또한, 본발명은온라인음성인식상황에서추정하는묵음구간의캡스트럼평균값과실제음성구간전체의캡스트럼평균값과의차이로인한음성인식성능저하를극복할수 있다.

公开(公告)号：KR1020110066622A

公开(公告)日：2011-06-17

申请号：KR1020090123354

申请日：2009-12-11

Applicant: 한국전자통신연구원

Inventor： 강점자 ,  이윤근 ,  정호영 ,  이성주 ,  강병옥 ,  박기영 ,  김종진 ,  박전규 ,  왕지현 ,  전형배 ,  정의석 ,  정훈 ,  박상규

IPC: G10L15/26 ,  G06F17/28 ,  G10L13/00

Abstract: PURPOSE: An international interpretation device and method thereof based on voice recognition are provided to supply text data or a synthetic voice which is interpreted in a native language to attendees. CONSTITUTION: A conference participant information registering unit(100) registers conference participant information including the language used by a conference participant. A voice recognition unit(200) registers a keyword according to the conference participant contents of presentations in advance. The voice recognition circuit outputs a voice recognition result of a keyword form. A language interpreting unit(300) performs conversion to a target language corresponding to a using language per conference participants.

Abstract translation: 目的：提供一种基于语音识别的国际解读装置及其方法，用于向参加者提供用母语解释的文本数据或合成语音。 组织：会议参与者信息登记单元（100）登记包括会议参与者使用的语言的会议参与者信息。 语音识别单元（200）预先根据演示的会议参与者内容登记关键字。 语音识别电路输出关键词形式的语音识别结果。 语言解释单元（300）根据每个会议参与者执行对应于使用语言的目标语言的转换。

公开(公告)号：KR1020110040632A

公开(公告)日：2011-04-20

申请号：KR1020100028110

申请日：2010-03-29

Applicant: 한국전자통신연구원

Inventor： 조승현 ,  이지현 ,  이종훈 ,  이한협 ,  이은구 ,  정의석 ,  이상수

IPC: H04B10/2581 ,  H04B10/43

CPC classification number: H04J14/0238 ,  H04B10/2519 ,  H04B10/2525 ,  H04B10/503

Abstract: PURPOSE: A passive optical scriber network system of a wavelength division multiplexing is provided to compensate a penalty by deterioration according a signal mode optical fiber transmission itself. CONSTITUTION: An OLT(Optical Line Terminal)(100) multiplexes the spectrum-divided light per wavelength after diving spectrum of the wideband non-interference light. The ONT(Optical Network Terminal)(200) receives an optical signal from the OLT. A remote node connects the OLT and the ONT. By using dispersion compensation fiber, a dispersion compensation module(170) compensates a relative intensity noise.

Abstract translation: 目的：提供一种波分复用的无源光划分器网络系统，以便根据信号模式光纤传输本身的劣化来补偿损失。 构成：OLT（光线路终端）（100）在宽带非干涉光的潜水光谱之后复用每波长频谱分割的光。 ONT（光网络终端）（200）从OLT接收光信号。 远程节点连接OLT和ONT。 通过使用色散补偿光纤，色散补偿模块（170）补偿相对强度噪声。

公开(公告)号：KR1020110034360A

公开(公告)日：2011-04-05

申请号：KR1020090091867

申请日：2009-09-28

Applicant: 한국전자통신연구원

Inventor： 이성주 ,  이윤근 ,  강병옥 ,  강점자 ,  박기영 ,  박전규 ,  왕지현 ,  전형배 ,  정의석 ,  정호영 ,  정훈 ,  김종진 ,  박상규

IPC: G10L21/0272 ,  G10L21/0208 ,  G10L15/20

Abstract: PURPOSE: A location tracing apparatus using user voice and method thereof are provided to reduce voice recognition degradation by echo sound and to integrate a sound source location determination technology. CONSTITUTION: A sound source determining unit(10) divides two channel signals by sound source. A stereo wiener filter unit(20) removes a noise from a sound source signal that is separated by the sound source determining unit. The stereo wiener filter unit filters a residual signal factor. A voice recognition unit(60) recognizes the voice of a user from the separated sound source signal and measures the reliability for a voice recognition result. A channel select unit(80) selects a target channel based on the reliability for the voice recognition result. A sound source location tracing unit(130) analyzes an interfere channel signal and a target channel signal.

Abstract translation: 目的：提供使用用户语音的位置跟踪装置及其方法，以减少由回声产生的声音识别劣化，并集成声源定位技术。 构成：音源决定单元（10）通过声源分割两声道信号。 立体声滤波器单元（20）从由声源确定单元分离的声源信号中去除噪声。 立体声维纳滤波器单元滤除残留信号因子。 语音识别单元（60）从分离的声源信号识别用户的声音，并测量语音识别结果的可靠性。 频道选择单元（80）基于语音识别结果的可靠性来选择目标频道。 声源位置跟踪单元（130）分析干扰信道信号和目标信道信号。

公开(公告)号：KR1020110018786A

公开(公告)日：2011-02-24

申请号：KR1020090076416

申请日：2009-08-18

Applicant: 한국전자통신연구원

Inventor： 정의석 ,  설동민 ,  김병휘 ,  이상수 ,  조승현

IPC: H04B10/2581 ,  H04B10/60

CPC classification number: H04B10/695 ,  H04J14/0282 ,  H04L25/062 ,  H04L27/06

Abstract: PURPOSE: An apparatus and a method for detecting optical signal are provided to use determination threshold value which optimized by the received signal. CONSTITUTION: An optical signal detection apparatus comprises a signal receiving part(210) for changing the received optical signal into the electric signal, and a signal detection(230) for detecting the transformed electric signal based on the optimized determination threshold value calculating. The determination threshold value decision unit establishes the mathematical model based on the transformed electric signal.

Abstract translation: 目的：提供一种用于检测光信号的装置和方法，以使用由接收信号优化的确定阈值。 一种光信号检测装置，包括用于将接收的光信号改变为电信号的信号接收部分（210），以及用于基于优化的确定阈值计算来检测变换的电信号的信号检测（230）。 确定阈值决定单元基于变换后的电信号建立数学模型。