-
公开(公告)号：KR1020130139095A
公开(公告)日：2013-12-20
申请号：KR1020120062835
申请日：2012-06-12
Applicant: 목포대학교산학협력단
CPC classification number: G06F3/167 , G06F17/30241 , G06Q50/14 , G10L15/22
Abstract: The present invention relates to an integrated tourism information providing device based on a voice user interface, and the integrated tourism information providing device according to the present invention evaluates the performance of a speech recognition function by measuring the word error rate in speech recognition, articulation of speech synthesis, and user satisfaction as well as comprehensively provides guidance on tour routes and adjacent tourist attractions as part of the coupling between the tourism sector and the ICT sector. According to the present invention, the mean word error rate can be reduced significantly, the mean accuracy in identifying pronunciations can be improved comparably, and useful information can be provided for a user based on a user satisfaction survey. [Reference numerals] (121) Geography database;(AA) Client;(BB) Network;(CC) Server;(DD) Tourist Attraction database
Abstract translation: 本发明涉及一种基于语音用户界面的综合旅游信息提供装置，并且根据本发明的综合旅游信息提供装置通过测量语音识别中的单词错误率来评估语音识别功能的性能， 语音综合和用户满意度，全面提供旅游线路和相邻旅游景点的指导，作为旅游部门与ICT行业耦合的一部分。 根据本发明，可以显着降低平均字错误率，可以比较地改善识别发音的平均精度，并且可以基于用户满意度调查为用户提供有用的信息。 （121）地理数据库;（AA）客户端;（BB）网络;（CC）服务器;（DD）旅游景点数据库
-
公开(公告)号：KR1020130037041A
公开(公告)日：2013-04-15
申请号：KR1020110101360
申请日：2011-10-05
Applicant: 목포대학교산학협력단
CPC classification number: G10L15/14 , G10L19/038 , G10L21/02
Abstract: PURPOSE: A sound model compensation method which combines mask based multi-channel sound separation for marine sound is provided to analyze noise and voice properties, thereby improving performance of voice recognition. CONSTITUTION: A noise model and a weighted value necessary for sound model adaptation are obtained by using an HMM based mask. Mask information is estimated from a binaural signal. Noise is decreased by using the mask. After MMSS(Mask-based Multi-channel Source Separation) is performed, a 13th MFCC(Mel Frequency Cepstral Coefficient) is extracted from a voice signal.
Abstract translation: 目的：提供一种组合基于屏蔽的多声道声音分离用于海洋声音的声音模型补偿方法，用于分析噪声和声音特性，从而提高语音识别的性能。 构成：通过使用基于HMM的掩模获得声音模型适应所需的噪声模型和加权值。 屏蔽信息由双耳信号估计。 使用面罩降低噪音。 在执行MMSS（基于掩码的多信道源分离）之后，从语音信号中提取第13个MFCC（Mel频率倒谱系数）。
-
公开(公告)号：KR1020150019530A
公开(公告)日：2015-02-25
申请号：KR1020130096552
申请日：2013-08-14
Applicant: 목포대학교산학협력단
IPC: G06Q50/14
Abstract: 본 발명은 대화형 음성 사용자 인터페이스 기반 육해상 통합관광정보 안내 시스템에 관한 것으로서, 본 발명에 따른 대화형 음성 사용자 인터페이스 기반 육해상 통합관광정보 안내 시스템은 해양 환경에서 대화형 음성 사용자 인터페이스의 입력 음성에 포함된 해상 잡음을 효과적으로 감쇄하며, 육해상 경로 통합 알고리즘을 포함하는 것을 특징으로 한다. 본 발명에 따르면, 해상 잡음에 강건한 대화형 음성 사용자 인터페이스를 이용하여 육해상 이동경로, 및 음성 관광 정보를 제공하는 시스템을 제안함으로써 다음의 효과를 얻을 수 있다. 첫째, 해상 잡음 감쇄 기술을 포함하는 대화형 음성 사용자 인터페이스를 통하여 선박 또는 해상 플랫폼 등의 해상 환경에서 사용자들이 신뢰성 있는 음성기반 상호작용을 통해 육해상 통합 관광정보를 취득할 수 있다. 둘째, 제안된 시스템의 육해상 경로 통합 알고리즘을 통해 새로운 육해상 통합 이동 경로의 DB를 구축할 필요 없이 기존의 육상 및 해상 경로 DB만으로 신뢰성 있는 육해상 통합 경로 정보를 제공할 수 있다.
Abstract translation: 本发明涉及一种基于交互式语音用户界面的综合陆/海旅游信息指导系统。 根据本发明，基于交互式语音用户接口的综合陆/海旅游信息指导系统有效地减少输入到海上环境中的交互语音用户接口的语音中包含的海噪声，并且包括陆/海路线 集成算法。 本发明提出了一种通过免受海上噪声的交互式语音用户界面提供陆/海移动路线和语音旅游信息的系统，从而实现以下效果：使用户能够通过可靠的基于语音的交互获得综合的陆/海旅游信息 在船舶，海上平台等海洋环境中使用配备海噪声技术的交互式语音用户界面; 并通过所提出的系统的陆/海路线集成算法，仅使用现有的陆路数据库和海上航行数据库提供可靠的陆地/海上路线信息，而不需要构建新的陆地/海上移动路线数据库。
-
Patent Agency Ranking
公开(公告)号：KR1020130034915A
公开(公告)日：2013-04-08
申请号：KR1020110099080
申请日：2011-09-29
Applicant: 목포대학교산학협력단
Abstract: PURPOSE: A method for efficiently reinforcing a voice signal based on a voice coding parameter in marine voice communications is provided to reinforce excitation signals among a bitstream parameter based on a voice encoding device in root environment, thereby supplying excellent performance. CONSTITUTION: An excitation signal gain ratio estimation unit(140) estimates an excitation signal gain ratio by using an excitation signal gain of background noises estimated by an excitation signal gain estimation block(130), and a decoding result which applies a fixed codebook gain by a fixed codebook vector decoding block(120). An excitation signal generation unit(150) generates an excitation signal by using a decoding result which applies an adaptive codebook gain by an excitation signal gain ratio estimation result and an adaptive codebook vector decoding block(110). [Reference numerals] (110,120) Adaptive codebook vector decoding; (130) Excitation signal gain estimation of background noise; (140) Excitation signal gain ratio estimation; (150) Excitation signal generation; (160) Linear prediction synthesis filter; (170) Postprocessor; (AA,BB) Input bit stream; (CC) Adaptive codebook gain application; (DD) Fixed codebook gain application; (EE) Enhanced voice signal; (FF) Near-end background noise estimation;
Abstract translation: 目的：提供一种在海洋语音通信中基于语音编码参数有效加强语音信号的方法，以加强基于根环境中的语音编码装置的比特流参数中的激励信号，从而提供出色的性能。 激励信号增益比估计单元（140）通过使用由激励信号增益估计块（130）估计的背景噪声的激励信号增益来估计激励信号增益比，以及解码结果，其通过 固定码本向量解码块（120）。 励磁信号生成单元（150）通过使用通过激励信号增益比估计结果应用自适应码本增益的解码结果和自适应码本矢量解码块（110）来产生激励信号。 （110,120）自适应码本矢量解码; （130）背景噪声的激励信号增益估计; （140）励磁信号增益比估计; （150）励磁信号发生; （160）线性预测合成滤波器; （170）后处理; （AA，BB）输入位流; （CC）自适应码本增益应用; （DD）固定码本增益申请; （EE）增强语音信号; （FF）近端背景噪声估计;
-
公开(公告)号：KR1020130037913A
公开(公告)日：2013-04-17
申请号：KR1020110102450
申请日：2011-10-07
Applicant: 목포대학교산학협력단
Abstract: PURPOSE: A code division multiplexing optical fiber Bragg lattice sensor network is provided to execute monitoring without a collision at the center by multiplexing information received from each sensor. CONSTITUTION: A first sensor and a second sensor sense signals. A reflective semiconductor optical amplifier amplifies the amplitude of a signal reflected from the first sensor and the second sensor. The first and the second sensor are mutually independent. The peak of a pulse outputted from the reflective semiconductor optical amplifier is linearly changed.
Abstract translation: 目的：提供码分复用光纤布拉格点阵传感器网络，通过复用从每个传感器接收的信息，在中心执行监控而不发生冲突。 构成：第一传感器和第二传感器检测信号。 反射半导体光放大器放大从第一传感器和第二传感器反射的信号的幅度。 第一和第二传感器是相互独立的。 从反射半导体光放大器输出的脉冲的峰值线性地变化。
-
公开(公告)号：KR1020130037040A
公开(公告)日：2013-04-15
申请号：KR1020110101359
申请日：2011-10-05
Applicant: 목포대학교산학협력단
Abstract: PURPOSE: A voice phishing detection method based on distinctive weighted value learning in marine/voice communication is provided to detect voice phishing without a separate feature vector extraction process by using only a parameter extracted in a process which changes a signal into a voice signal. CONSTITUTION: An SMV(Selectable Mode Vocoder) decoder comprises a new feature vector by using a feature vector which is extracted in a process which changes an LSF(Line Spectral Frequency) into an LPC(Linear Prediction Coding); and a feature vector extracted in a process which changes the obtained LPC into a voice signal. The SMV decoder calculates likelihood for the transmitted bitstream by using a GMM(Gaussian Mixture Model) and selects a flag for a value with the maximum likelihood.
Abstract translation: 目的：提供一种基于海洋/语音通信中特色加权值学习的语音网络钓鱼检测方法，通过仅使用将信号改变为语音信号的过程中提取的参数，无需单独的特征向量提取过程来检测语音网络钓鱼。 构成：SMV（可选模式声码器）解码器通过使用在将LSF（线谱频率）改变为LPC（线性预测编码）的处理中提取的特征向量来包括新特征向量; 以及在将所获得的LPC改变为语音信号的处理中提取的特征向量。 SMV解码器通过使用GMM（高斯混合模型）来计算所发送的比特流的可能性，并且选择具有最大似然度的值的标志。
-
7.发明公开베이스 노드의 이동성이 높은 센서 네트워크에서 지역 탐색 알고리즘을 이용한 에너지 효율적인 신장 트리 기반 라우팅 방법 无效使用本地搜索算法在高速移动台站的无线传感器网络中基于传播树的能量有效路由
公开(公告)号：KR1020120044704A
公开(公告)日：2012-05-08
申请号：KR1020100106144
申请日：2010-10-28
Applicant: 목포대학교산학협력단
IPC: H04L12/28
CPC classification number: Y02D30/20
Abstract: PURPOSE: A spanning tree based routing method using a local searching algorithm in a high mobility sensor network is provided to improve network utilization by providing an effective local searching algorithm. CONSTITUTION: An MST(Minimal Spanning Tree) is used as a start point of local searching(S210). A proximity solution is created(S220). Numbers of wiener are calculated for the proximity solution(S230). A tree including the smallest numbers of the wiener in the proximity solution are searched(S240). The numbers of the wiener is not changed, the tree which is acquired at the last is determined as the solution.
Abstract translation: 目的：提供一种在高移动性传感器网络中使用局部搜索算法的基于生成树的路由方法，通过提供有效的局部搜索算法来提高网络利用率。 构成：使用MST（最小生成树）作为本地搜索的起始点（S210）。 创建邻近解决方案（S220）。 计算邻近解的数量（S230）。 搜索包括接近解中的最小维数的树（S240）。 维纳人的数量没有改变，最后得到的树被确定为解。
-
公开(公告)号：KR1020130039154A
公开(公告)日：2013-04-19
申请号：KR1020110103643
申请日：2011-10-11
Applicant: 목포대학교산학협력단
Abstract: PURPOSE: A sensor using a self-injection locked reflective semiconductor optical amplifier for measuring marine temperature and strain is provided to measure changes in temperature and strain based on the power of an optical bragg lattice as the power of an optical fiber bragg lattice is linearly changed according to changes in the temperature and strain. CONSTITUTION: A sensor using a self-injection locked reflective semiconductor optical amplifier for measuring marine temperature and strain comprises a reflective semiconductor light amplifier(110), a variable optical fiber bragg grating(130), optical fiber bragg gratings(160-200), and a light spectrum analyzer(140). The reflective semiconductor light amplifier is self-injection locked. The variable optical fiber bragg grating generates variable laser sources by self-injection locking the reflective semiconductor light amplifier. [Reference numerals] (110) Reflective semiconductor light amplifier; (140) Light spectrum analyzer;
Abstract translation: 目的：提供一种用于测量海洋温度和应变的自注射锁定反射半导体光学放大器的传感器，用于测量基于光学布拉格点阵的功率的温度和应变的变化，因为光纤布拉格晶格的功率是线性变化的 根据温度和应变的变化。 构成：使用用于测量海洋温度和应变的自注射锁定反射半导体光学放大器的传感器包括反射半导体光放大器（110），可变光纤布拉格光栅（130），光纤布拉格光栅（160-200）， 和光谱分析器（140）。 反射半导体光放大器是自注射锁定的。 可变光纤布拉格光栅通过自发注入锁定反射半导体光放大器来产生可变激光源。 （附图标记）（110）反射半导体光放大器; （140）光谱分析仪;
-
-
-
-
-
-
-
Search Results
8
records
(took 0.016 seconds)
