-
公开(公告)号：KR1020100072842A
公开(公告)日：2010-07-01
申请号：KR1020080131369
申请日：2008-12-22
Applicant: 한국전자통신연구원
CPC classification number: G10L21/0208 , G10L15/20 , G10L25/48
Abstract: PURPOSE: A speech improving apparatus and a speech recognition system and method are provided to improve the voice recognition performance of a voice recognition system in a movable body of small resources by performing signal decoding through a sound model database. CONSTITUTION: A speed level divider(100) measures a moving speed level of a movable body through an inputted noise signal inputted in an initial stage of voice recognition. When the speed level of the movable body is lower than a predetermined value, a first sound quality improvement unit(112) improves the sound quality of a voice signal inputted by a Wiener filter. If the speed level of the movable body exceeds a predetermined value, a second sound quality improvement unit(114) improves the sound quality of a voice signal inputted by a GMM(Gaussian Mixture Model).
Abstract translation: 目的：提供语音改善装置和语音识别系统和方法，通过声音模型数据库执行信号解码来提高小资源移动体中语音识别系统的语音识别性能。 构成：速度分级器（100）通过在语音识别的初始阶段输入的输入噪声信号测量可移动体的移动速度水平。 当可移动体的速度水平低于预定值时，第一音质改善单元（112）提高了由维纳滤波器输入的语音信号的声音质量。 如果可移动体的速度水平超过预定值，则第二音质改善单元（114）提高了由GMM（高斯混合模型）输入的语音信号的声音质量。
-
公开(公告)号：KR1020100069117A
公开(公告)日：2010-06-24
申请号：KR1020080127707
申请日：2008-12-16
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A CMS(Cepstrum Mean Subtraction) method and a device thereof are provided to accurately normalize a channel property by estimating an average CMS value of the real voice section based on the CMS average value of a mute section. CONSTITUTION: A property extractor(200) extracts the properties of a mute section before a start point, a sound section, and a mute section after a finish point. A firing unit CMS value calculator(600) calculates an actual firing unit cepstrum average about the entire sound section. A cepstrum average estimator(300) estimates the cepstrum average of the entire section based on the properties of the mute section. A property vector CMS applier(400) performs channel-normalization of the estimated average. A decoder decodes the channel-normalized MFCC property vector.
Abstract translation: 目的：提供CMS（倒谱平均减法）方法及其装置，以通过基于静音部分的CMS平均值估计真实语音部分的平均CMS值来准确地规范信道特性。 规定：属性提取器（200）在完成点之后提取起始点，声音部分和静音部分之前的静音部分的属性。 点火单元CMS值计算器（600）计算关于整个声音部分的实际发射单位倒谱平均值。 倒谱平均估计器（300）基于静音部分的属性来估计整个部分的倒谱平均值。 属性向量CMS应用程序（400）执行估计平均值的信道归一化。 解码器解码信道归一化的MFCC属性向量。
-
公开(公告)号：KR1020100066917A
公开(公告)日：2010-06-18
申请号：KR1020080125434
申请日：2008-12-10
Applicant: 한국전자통신연구원
CPC classification number: G01C21/3608 , G01C21/3611 , G01C21/3629 , G06F17/3074 , G10L15/18 , G10L15/22
Abstract: PURPOSE: A voice recognition method of a vehicle navigation terminal is provided to generate voice emitting isoform through a simple pattern construction using a resolute/tagged result by presenting a meaning classification system for POI name domain. CONSTITUTION: A voice recognition method of a vehicle navigation terminal is as follows. The points of interest(POI) list and POI learning data are recognized from the voice information of a voice emitting isoform input to the vehicle navigation terminal (S200). A resource is built on the POI list and the POI learning data recognized(S202). The resolution and tagging on the built resource are performed with the POI list(S204). The result resolved and tagged is created as POI database(S206). Simplex/analyzed database is built based on the POI list and the POI learning data. N-gram vocabulary is extracted from the POI learning data.
Abstract translation: 目的：提供一种车载导航终端的语音识别方法，通过呈现POI名称域的意义分类系统，通过简单的模式构造，通过坚决/标记的结果生成语音发射同种型。 构成：车辆导航终端的声音识别方法如下。 通过输入到车辆导航终端的发音同步体的语音信息来识别兴趣点（POI）列表和POI学习数据（S200）。 资源建立在POI列表和POI学习数据识别（S202）上。 使用POI列表执行内置资源的分辨率和标记（S204）。 解决和标记的结果被创建为POI数据库（S206）。 基于POI列表和POI学习数据构建Simplex /分析数据库。 从POI学习数据中提取N-gram词汇表。
-
公开(公告)号：KR1020100065811A
公开(公告)日：2010-06-17
申请号：KR1020080124371
申请日：2008-12-09
Applicant: 한국전자통신연구원
IPC: G10L15/10 , G10L15/28 , G10L21/0272 , G10L15/20
CPC classification number: G10L15/20 , G10L21/0272 , G10L2021/02166
Abstract: PURPOSE: A speech recognition apparatus using source separation and source identification and a method therefor are provided to use a voice identifying device even under an environment with noise of point source types, thereby realizing various application systems of the voice identifying device. CONSTITUTION: A sound source separator divides mixed signals into sound source signals by independent elements analysis. The sound source separator extracts DOA(Direction Of Arrival) information of the divided sound source signals. A voice indentifying device(108) calculates the divided sound source signals by normalized log likelihood probability values. A user voice signal identifying device(112) uses reliability of voice signal identification to identify a sound source corresponding to a voice signal of a user.
Abstract translation: 目的：提供一种使用源分离和源标识的语音识别装置及其方法，即使在具有点源类型噪声的环境下也能使用语音识别装置，从而实现语音识别装置的各种应用系统。 构成：声源分离器通过独立元素分析将混合信号分为声源信号。 声源分离器提取分割声源信号的DOA（到达方向）信息。 语音识别装置（108）通过归一化对数似然概率值计算划分的声源信号。 用户语音信号识别装置（112）使用语音信号识别的可靠性来识别对应于用户的语音信号的声源。
-
公开(公告)号：KR100930714B1
公开(公告)日：2009-12-09
申请号：KR1020070130950
申请日：2007-12-14
Applicant: 한국전자통신연구원
CPC classification number: G10L15/187 , G10L2015/025
Abstract: 음성인식 장치는 상기 음성 신호에 대응하는 특징벡터열을 생성하고, 음소에 해당하는 음향 및 언어 모델을 이용하여 특징 벡터열에 대응하는 음소열을 인지한다. 그리고 음성인식 장치는 인지한 음소열에 대응하는 어휘를 인지한다. 이때 음소 언어모델은 음소들간의 연결관계를 나타내며 음소의 시변 특성에 따라 모델링한 것이다.
음성 인식, n-그램, 시변 특성, 편집거리Abstract translation: 语音识别装置识别通过使用声学和语言模型来生成对应于所述打开的语音信号的特征矢量，对应于音素对应于列特征向量的音素列。 语音识别设备识别与识别的音素串对应的词汇。 在这种情况下，音素语言模型代表了音素之间的连接关系，并根据音素的时变特征进行建模。
-
Patent Agency Ranking
公开(公告)号：KR100930587B1
公开(公告)日：2009-12-09
申请号：KR1020070122185
申请日：2007-11-28
Applicant: 한국전자통신연구원
IPC: G10L15/01 , G10L15/10 , G10L15/187
Abstract: A confusion matrix based utterance verification method and an apparatus thereof are provided to select a phoneme with high discrimination by using a probability value of a confusion matrix as a weight for a likelihood value of a mono phone model. By performing viterbi decoding by using a context dependent phoneme mode, an inputted voice is recognized(307). A likelihood value of each phoneme, included in a pre-trained context independence phoneme model, and each phoneme, included in the voice-recognized character string as a voice recognition result, is calculated(309). Reliability for the voice-recognized character string is measured based on the calculated likelihood value of each phoneme and the pre-calculated probability value of the confusion matrix(311). It is determined whether to grant or reject the voice-recognized character string based on the measured reliability(313,315,317).
Abstract translation: 提供基于混淆矩阵的发声验证方法及其装置，以通过使用混淆矩阵的概率值作为单声道手机型号似然值的权重来选择具有高判别度的音素。 通过使用上下文相关音素模式进行维特比解码，识别输入的语音（307）。 计算（309）包括在预先训练的上下文独立音素模型中的每个音素的似然值以及包括在作为语音识别结果的语音识别字符串中的每个音素。 基于计算出的每个音素的似然值和混淆矩阵的预先计算的概率值来测量语音识别字符串的可靠性（311）。 基于测量的可靠性来确定是否授予或拒绝语音识别字符串（313,315,317）。
-
公开(公告)号：KR1020090111739A
公开(公告)日：2009-10-27
申请号：KR1020080075653
申请日：2008-08-01
Applicant: 한국전자통신연구원
IPC: G10L15/20
Abstract: PURPOSE: A noise cancelling apparatus is provided to estimate a clean voice more accurately in an environment in which a dynamic noise and various noises are mixed. CONSTITUTION: A noise cancelling apparatus comprises a noise estimation module(200) which calculates the estimation value of a noise signal in the current frame of a voice signal, a Wiener filter module(202) which receives the voice signal and calculates an intermediate result by applying the intermediate Wiener filter, a database(206) in which Gaussian mixed-model data is stored, and an MMSE estimation module(204) which calculates the estimation value of a clean voice by using the Gaussian mixed-model data and intermediate result.
Abstract translation: 目的：提供一种噪声消除装置，用于在动态噪声和各种噪声混合的环境中更精确地估计干净的声音。 噪声消除装置包括噪声估计模块（200），噪声估计模块（200），其计算语音信号的当前帧中的噪声信号的估计值;维纳滤波器模块（202），其接收语音信号并通过以下步骤计算中间结果 应用中间维纳滤波器，存储高斯混合模型数据的数据库（206）和通过使用高斯混合模型数据和中间结果来计算干净声音的估计值的MMSE估计模块（204）。
-
公开(公告)号：KR1020090063546A
公开(公告)日：2009-06-18
申请号：KR1020070130950
申请日：2007-12-14
Applicant: 한국전자통신연구원
CPC classification number: G10L15/187 , G10L2015/025
Abstract: A voice recognition device and a method thereof are provided to perform a decoding process in syllable unit, thereby improving voice recognition speed. A feature vector chain corresponding to a speech signal is produced(S200). A phoneme chain corresponding to the feature vector chain is recognized by using a phoneme language model(S300). The phoneme language model shows a connected relation between phonemes. The phoneme language model is made by considering positions where each phoneme is arranged in a random vocabulary. With regard to plural phonemes recognized at random time, the phoneme language model refers to a probability of recognizing one of the phonemes while previous phonemes are recognized. A vocabulary corresponding to the phoneme chain is recognized(S400).
Abstract translation: 提供语音识别装置及其方法，以在音节单元中执行解码处理，从而提高语音识别速度。 产生对应于语音信号的特征向量链（S200）。 通过使用音素语言模型识别对应于特征向量链的音素链（S300）。 音素语言模型显示了音素之间的连接关系。 音素语言模型是通过考虑每个音素在随机词汇中排列的位置来做出的。 关于在随机时间识别的多个音素，音素语言模型是指在识别先前的音素时识别一个音素的概率。 识别与音素链对应的词汇（S400）。
-
公开(公告)号：KR1020090055320A
公开(公告)日：2009-06-02
申请号：KR1020070122185
申请日：2007-11-28
Applicant: 한국전자통신연구원
IPC: G10L15/01 , G10L15/10 , G10L15/187
Abstract: A confusion matrix based utterance verification method and an apparatus thereof are provided to select a phoneme with high discrimination by using a probability value of a confusion matrix as a weight for a likelihood value of a mono phone model. By performing viterbi decoding by using a context dependent phoneme mode, an inputted voice is recognized(307). A likelihood value of each phoneme, included in a pre-trained context independence phoneme model, and each phoneme, included in the voice-recognized character string as a voice recognition result, is calculated(309). Reliability for the voice-recognized character string is measured based on the calculated likelihood value of each phoneme and the pre-calculated probability value of the confusion matrix(311). It is determined whether to grant or reject the voice-recognized character string based on the measured reliability(313,315,317).
Abstract translation: 提供了一种基于混淆矩阵的话音验证方法及其装置，通过使用混淆矩阵的概率值作为单声道电话机型的似然值的权重来选择具有高辨别力的音素。 通过使用与上下文相关的音素模式进行维特比解码，识别输入的语音（307）。 计算包括在预先训练的上下文独立音素模型中的每个音素的可能性值，以及包括在作为语音识别结果的语音识别字符串中的每个音素（309）。 基于所计算的每个音素的似然值和混淆矩阵的预先计算的概率值来测量语音识别字符串的可靠性（311）。 确定是否基于测量的可靠性来授予或拒绝语音识别的字符串（313,315,317）。
-
公开(公告)号：KR100845428B1
公开(公告)日：2008-07-10
申请号：KR1020060081027
申请日：2006-08-25
Applicant: 한국전자통신연구원
IPC: G10L15/14 , G10L15/183 , G10L15/28
CPC classification number: G10L15/142 , G10L2015/025
Abstract: 본 발명은 음성이 서로 독립적인 2개의 잡음 채널(음향 변이 채널 및 발음 변이 채널)을 통해 발성된다고 가정하고(전통적인 음성인식에서는 1개의 잡음채널로 음성이 발성된다고 가정함), 이 발성된 음성을 개별적으로 복호화함으로써 인식 대상 어휘가 증가하게 될 경우에도 고속으로 음성 인식을 가능하게 하기 위한 것으로, 이를 위한 본 발명은, 입력수단으로부터 입력되는 신호 중 음성신호만을 검출하여 특징 파라메타로 변환하고, 변환된 특징 파라메타와 기설정된 해당 모델들을 이용하여 제1복호화 과정 식에 적용 및 1차 비터비 디코딩시켜 변이 음소열을 산출하는 음향 변이 채널 수단과, 1차 디코딩된 변이 음소열과, 기세팅되어 분리된 DHMM 기반 문맥종속 오류 모델을 이용하여 제2복호화 과정 식에 적용 및 2차 비터비 디코딩시켜 단어 음소열을 산출하는 발음 변이 채널 수단을 포함한다. 그리고, 제한된 저장매체 환경에서도 대규모 어휘에 대한 탐색 공간을 필요한 부분만을 예측하는 동적 적재 방식을 사용해 연산에 필요한 부분만을 저장매체 상에 적재할 수 있어 저장매체 사용량을 최소화할 수 있는 효과가 있다.
음성, 변이 음소열, 단어 음소열, 음향 변이 채널, 발음 변이 채널
-
-
-
-
-
-
-
-
-
Search Results
210
records
(took 0.029 seconds)
