-
公开(公告)号：KR1020100072744A
公开(公告)日：2010-07-01
申请号：KR1020080131236
申请日：2008-12-22
Applicant: 한국전자통신연구원
IPC: H04N21/422 , G06F3/16 , G10L15/28
CPC classification number: H04N21/42212 , G06F3/16 , G10L15/28
Abstract: PURPOSE: A remote controller, a method and an apparatus for controlling an input interface are provided to enable a user to conveniently input a Hangul, English, number and symbol character through a keypad. CONSTITUTION: An input keypad(1100) combines two keys among a number key, an asteroid key, a sharp key, a directional key and a special character key. The input keypad selects one of input among the Hangul, English and number characters and symbol, and a control unit(1200) recognizes a key operation through the input keypad. The control unit process a key signal corresponding to the recognized key operation, and a wireless transmission unit(1400) transmits the key signal processed in the control unit.
Abstract translation: 目的：提供用于控制输入接口的遥控器，方法和装置，以使用户能够通过键盘方便地输入韩文，英文，数字和符号字符。 构成：输入键盘（1100）组合数字键，小行星键，锐利键，方向键和特殊字符键中的两个键。 输入键盘选择韩文，英文和数字字符和符号中的一个输入，控制单元（1200）通过输入键盘识别键操作。 控制单元处理与所识别的键操作对应的键信号，无线发送单元（1400）发送在控制单元中处理的键信号。
-
公开(公告)号：KR1020100068530A
公开(公告)日：2010-06-24
申请号：KR1020080126924
申请日：2008-12-15
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A rejection apparatus and a method of a garbage and anti-word model base in voice recognition are provided to effectively reject various operating noise or an unenrolled word by implementing a rejection process about a recognized word. CONSTITUTION: An extracting unit(104) extracts a feature vector from a voice signal. A searcher(110) gives a score through a pattern matching about the feature vector and outputs a recognition result. A rejection network generator(114) generates 'the rejection network for a rejection evaluation' through the recognition result. A rejection searcher(124) outputs a recognition score of 'word model comprising the rejection network' based on a garbage sound model. A decision logic unit(128) decides the rejection about the recognized word comparing with the recognition scores.
Abstract translation: 目的：提供语音识别中的垃圾和反词模型的拒绝装置和方法，以通过对识别的字进行拒绝处理来有效地拒绝各种操作噪声或未注册的单词。 构成：提取单元（104）从语音信号中提取特征向量。 搜索者（110）通过与特征向量匹配的模式给出得分，并输出识别结果。 拒绝网络发生器（114）通过识别结果产生“拒绝评估的拒绝网络”。 拒绝搜索器（124）基于垃圾声音模型输出包括拒绝网络的单词模型的识别分数。 决定逻辑单元（128）决定与识别分数相比的所识别的字的拒绝。
-
公开(公告)号：KR1020100066918A
公开(公告)日：2010-06-18
申请号：KR1020080125435
申请日：2008-12-10
Applicant: 한국전자통신연구원
IPC: H04L12/28
CPC classification number: H04L12/2812
Abstract: PURPOSE: A home network service method using a ubiquitous intelligent robot for offering a service for a location of a user and a robot for the coordinate information are provided to no need to use a remote controller by supplying robot performing voice input through a location sensor. CONSTITUTION: User interface information is inputted through a ubiquitous intelligent robot. The inputted user interface information is transmitted to the ubiquitous intelligent robot server(S300, S302). The ubiquitous intelligent robot server refers to the multimedia device having the multimedia information corresponding to the user interface information from a home network device group(S304). If the multimedia device is detected, the information search result user interface information is outputted through the ubiquitous intelligent robot.
Abstract translation: 目的：通过提供通过位置传感器执行语音输入的机器人，无需使用遥控器，使用无处不在的智能机器人为用户和机器人的位置提供坐标信息的家庭网络服务方法。 构成：通过无处不在的智能机器人输入用户界面信息。 输入的用户界面信息被发送到无处不在的智能机器人服务器（S300，S302）。 无处不在的智能机器人服务器是指具有与来自家庭网络设备组的用户界面信息相对应的多媒体信息的多媒体设备（S304）。 如果检测到多媒体设备，则通过无处不在的智能机器人输出信息搜索结果用户界面信息。
-
94.发明公开
公开(公告)号：KR1020100062831A
公开(公告)日：2010-06-10
申请号：KR1020090027532
申请日：2009-03-31
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A multiple recognition candidate formation apparatus and a method thereof are provided, which can improve the efficiency of the voice recognition engine by reducing the usage amount of a memory unit and search time for creating the multiple recognition candidate. CONSTITUTION: A voice feature extractor(502) creates the feature vector through the voice recognition about the consecutive numbers voice. A search unit(504) creates the single recognition candidate string through the pattern recognition about the feature vector. The search unit outputs the likelihood point and feature vector about discrete numerical sound composed of the single recognition candidate string. A multiple recognition candidate generation part(508) creates the multiple recognition candidate by referring the order by numerical sound of the confidence measure generator(506) and the pre-set confusion matrix.
Abstract translation: 目的：提供一种多重识别候选者形成装置及其方法，其通过减少存储单元的使用量和创建多个识别候选者的搜索时间来提高语音识别引擎的效率。 构成：语音特征提取器（502）通过关于连续数字语音的语音识别来创建特征向量。 搜索单元（504）通过关于特征向量的模式识别创建单个识别候选串。 搜索单元输出关于由单个识别候选串组成的离散数字声音的似然点和特征向量。 多重识别候选产生部分（508）通过将置信度测量发生器（506）的数字声音和预设混淆矩阵参考顺序来创建多个识别候选。
-
公开(公告)号：KR1020090041923A
公开(公告)日：2009-04-29
申请号：KR1020070107705
申请日：2007-10-25
Applicant: 한국전자통신연구원
IPC: G10L15/06 , G10L15/02 , G10L15/183 , G10L15/197
Abstract: A voice recognition method is provided to model various textual language phenomenons into statistical modeling among various knowledge sources. A morpheme is interpreted for a primitive text language corpus consisting of the separate words of Korean(S201). A morpheme language corpus separated is a separate word generated to morpheme. A word trigram which is the language model consisting of a morpheme unigram about a generated morpheme language corpus as described above, and bigram and trigrams is generated(S202). A first N - best recognition candidate to the maximum N is generated for a voice(S204). Recognition result candidates applying a morph-syntactic constraints are revaluated(S205). A second N-best list generated in above step is revaluated(S206). A final N-best list is generated.
Abstract translation: 提供语音识别方法，将各种文本语言现象建模成各种知识源之间的统计建模。 语素被解释为由韩语单词组成的原始文本语言语料库（S201）。 分离语素语言语料是一个单独的语素词。 生成由上述生成的语素语言语料库的词素单词组成的语言模型的单词trigram，并且生成二进制和三元组（S202）。 为语音产生最大N的第N个最佳识别候选（S204）。 重新评估应用变形语法约束的识别结果候选（S205）。 在上述步骤中生成的第二个N最佳列表被重新评估（S206）。 生成最终的N最佳列表。
-
Patent Agency Ranking
公开(公告)号：KR1020090030063A
公开(公告)日：2009-03-24
申请号：KR1020070095375
申请日：2007-09-19
Applicant: 한국전자통신연구원
Inventor： 이성주
IPC: G10L25/93 , G10L21/0208
CPC classification number: G10L25/78
Abstract: A method for distinguishing the voice by using the voiced sound features of the human voice and an apparatus therefor are provided to overcome a problem that the performance of the existing voice and non-voice determining techniques is degraded in the actual noise environment. An input signal sound-quality enhancing part(201) removes additional noise from a sound signal including a voice signal and noise signal to minimize the phenomenon that the sound quality of the input signal is degraded by the additional noise. A voiced sound feature detecting part(205) extracts voiced sound features based on the voice signal received from the sound-quality enhancing part. A voiced sound/unvoiced sound determining model part(207) stores the threshold value or critical value of the voiced sound features extracted from a pure voice model in which the noise is not included. A voiced sound/unvoiced sound determining unit(209) compares 11 voiced sound features extracted by the voiced sound feature detecting part with the stored threshold value or critical value.
Abstract translation: 提供了通过使用人类语音的有声声音特征和其装置来区分语音的方法，以克服现有语音和非语音确定技术的性能在实际噪声环境中降级的问题。 输入信号声音质量增强部分（201）从包括语音信号和噪声信号的声音信号中去除附加噪声，以最小化输入信号的声音质量被附加噪声降级的现象。 有声声音特征检测部（205）基于从声音质量提高部接收到的语音信号，提取有声声音特征。 有声音/无声声音确定模型部分（207）存储从不包括噪声的纯语音模型中提取的有声声音特征的阈值或临界值。 有声音/无声声音确定单元（209）将由浊音特征检测部分提取的11个声音特征与所存储的阈值或临界值进行比较。
-
公开(公告)号：KR1020080030140A
公开(公告)日：2008-04-04
申请号：KR1020060095820
申请日：2006-09-29
Applicant: 한국전자통신연구원
Inventor： 이성주
IPC: G06F17/10
CPC classification number: G10L25/78
Abstract: A method for estimating priori speech absence probability based on a statistical model is provided to enable more accurate priori speech absence probability estimation by applying nonlinear property to the priori speech absence probability. Observation signal log energy is obtained(S110), and noise signal log energy is obtained(S120). A posteriori signal-noise ratio is obtained by using the observation signal log energy and the noise signal log energy(S130). A local and a global averages of the posteriori signal-noise ratio of a log scale are obtained(S140). A local and a global parameters are obtained by applying a sigmoid function and threshold value decision about the local and global averages(S145). A frame average of the posteriori signal-noise ratio of the log scale is obtained(S150). An average parameter is obtained by using the frame average of the posteriori signal-noise ratio of the log scale(S155). An instant speech absence probability is obtained by using the local parameter, the global parameter and the average parameter(S170). The priori speech absence probability is obtained by using the instant speech absence probability(S180).
Abstract translation: 提供了一种基于统计模型估计先验语音缺失概率的方法，以通过对先验语音不存在概率应用非线性特性来实现更准确的先验语音缺失概率估计。 获得观测信号对数能（S110），得到噪声信号对数能（S120）。 通过使用观测信号对数能量和噪声信号对数能量来获得后验信噪比（S130）。 获得对数标度的后验信噪比的局部和全局平均值（S140）。 通过应用关于局部和全局平均值的S形函数和阈值决策来获得局部和全局参数（S145）。 获得对数标度的后验信噪比的帧平均值（S150）。 通过使用对数标度的后验信号噪声比的帧平均值来获得平均参数（S155）。 通过使用局部参数，全局参数和平均参数（S170）获得即时言语缺席概率。 通过使用即时言语缺席概率获得先验语音缺失概率（S180）。
-
公开(公告)号：KR1020050019686A
公开(公告)日：2005-03-03
申请号：KR1020030057646
申请日：2003-08-20
Applicant: 한국전자통신연구원
Inventor： 이성주
IPC: G10L15/20
Abstract: PURPOSE: An additional noise removing apparatus using a human auditory model is provided to improve the performance of a speech recognition system by applying the human auditory model to an input audio signal at a pre-processing step for removing an additional noise. CONSTITUTION: An additional noise removing apparatus using a human auditory model includes a buffering an framing unit(10), a human auditory model application unit(100), a frequency spectrum estimator(40), an additional noise estimator(30), and an additional noise removing unit(50). The buffering and framing unit buffers an input audio signal and segments the audio signal into frames at a predetermined time interval. The human auditory model application unit applies the human auditory model to the input audio signal. The frequency spectrum estimator transforms the input audio signal into a frequency domain to generate a frequency spectrum composed of an amplitude component and a phase component. The additional noise estimator estimate spectrum information of a noise added to the audio signal using the frequency spectrum. The additional noise removing unit removes the additional noise estimated by the additional noise estimator from the frequency spectrum.
Abstract translation: 目的：提供一种使用人类听觉模型的附加噪声消除装置，以通过在预处理步骤中将人类听觉模型应用于输入音频信号来提高语音识别系统的性能，以消除附加噪声。 构成：使用人体听觉模型的附加噪声去除装置包括缓冲成帧单元（10），人类听觉模型应用单元（100），频谱估计器（40），附加噪声估计器（30）和 附加噪声去除单元（50）。 缓冲和成帧单元缓冲输入音频信号并以预定的时间间隔将音频信号分段成帧。 人类听觉模型应用单元将人体听觉模型应用于输入音频信号。 频谱估计器将输入音频信号转换成频域以产生由振幅分量和相位分量组成的频谱。 附加噪声估计器估计使用频谱加到音频信号的噪声的频谱信息。 附加噪声去除单元从频谱除去由附加噪声估计器估计的附加噪声。
-
公开(公告)号：KR1020040054843A
公开(公告)日：2004-06-26
申请号：KR1020020081153
申请日：2002-12-18
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A method for converting time shaft of a voice signal is provided to apply three level center clipping and a level crossing method to a synthesis voice signal and an analysis voice signal and then perform synchronization, thereby capable of reducing an amount of calculation by canceling a normalization portion and reducing a search period. CONSTITUTION: An analysis voice frame is initialized as a synthesis voice frame(S1). Thereafter, when all voice data are inputted(S2), a time shaft conversion method is finished. When all voice data are not inputted, a clipping level of the synthesis voice frame and the analysis voice frame is determined(S3). The synthesis voice frame and the analysis voice frame are divided into three levels by using the determined clipping level(S4). A level crossing point of the synthesis voice frame and the analysis voice frame is searched(S5). A synchronization point between the synthesis voice frame and the analysis voice frame is searched by using the analysis voice signal, the synthesis voice signal and the level crossing point processed through a three level center clipping process(S6). On the basis of the searched synchronization point, the synthesis voice signal and the analysis voice signal are rearranged. Two signals are superposed and added(S7).
Abstract translation: 目的：提供一种用于转换语音信号的时间轴的方法，将三级中心限幅和电平交叉方式应用于合成语音信号和分析语音信号，然后进行同步，从而能够减少计算量 归一化部分并减少搜索周期。 构成：分析语音帧被初始化为合成语音帧（S1）。 此后，当输入所有语音数据（S2）时，完成时间轴转换方法。 当不输入所有语音数据时，确定合成语音帧和分析语音帧的限幅电平（S3）。 通过使用确定的限幅电平将合成语音帧和分析语音帧分成三个等级（S4）。 搜索合成语音帧和分析语音帧的级别交叉点（S5）。 通过使用通过三级中心裁剪处理处理的分析语音信号，合成语音信号和电平交叉点来搜索合成语音帧和分析语音帧之间的同步点（S6）。 在搜索到的同步点的基础上，合成语音信号和分析语音信号被重新排列。 叠加并添加两个信号（S7）。
-
-
-
-
-
-
-
-
-
Search Results
127
records
(took 0.033 seconds)
