-
公开(公告)号：KR1020130100607A
公开(公告)日：2013-09-11
申请号：KR1020120021976
申请日：2012-03-02
Applicant: 삼성전자주식회사
CPC classification number: A61B8/5207 , A61B8/5269 , G01S7/52046 , G01S7/52047 , G01S15/8977
Abstract: PURPOSE: An ultrasonic wave image generation device offers excellent signal to noise ratio (SNR) and good resolution in a lateral and an elevation direction. CONSTITUTION: An ultrasonic wave image generation device (100) comprises a transceiver (110), a beam forming unit (120), and a point spread function (PSF) estimation unit (130). The beam forming unit calculates the received signals. The transceiver receives an echo signal and transmits an ultrasonic wave signal to an object. The PSF estimation unit updates and estimates a PSF according to each multi scale level. [Reference numerals] (110) Transceiver; (120) Beam forming unit; (130) PSF estimation unit; (140) Rendering unit
Abstract translation: 目的：超声波图像生成装置在横向和高度方向提供优异的信噪比（SNR）和良好的分辨率。 构成：超声波图像产生装置（100）包括收发器（110），波束形成单元（120）和点扩散功能（PSF）估计单元（130）。 波束形成单元计算接收信号。 收发器接收回波信号并将超声波信号发送到对象。 PSF估计单元根据每个多尺度级别来更新和估计PSF。 （附图标记）（110）收发器; （120）梁形成单元; （130）PSF估计部; （140）渲染单元
-
公开(公告)号：KR1020130054743A
公开(公告)日：2013-05-27
申请号：KR1020110120315
申请日：2011-11-17
Applicant: 삼성전자주식회사 , 한림대학교 산학협력단
CPC classification number: A61B8/14 , A61B8/5207 , G01S7/52047 , G01S15/8977
Abstract: PURPOSE: A beam forming method, an apparatus performing the same, and a medical image system are provided to remarkably reduce a calculation quantity which needs to be processed. CONSTITUTION: A beam forming apparatus(100) comprises a storage unit(110), a weighting factor calculating unit(120), and a synthesizing unit(130). The storage unit stores multiple basis vectors which are obtained from a beam forming coefficient of a premeasured echo signal. The weighting factor calculating unit produces a weighting factor which is applied to the echo signal reflected from a subject by using multiple stored basis vectors. The synthesizing unit applies the produced weighting factor to the echo signal which is reflected from the subject by using multiple stored base vectors and synthesizes signals to which the weighting factor is applied. [Reference numerals] (110) Storage unit; (120) Weighting factor calculating unit; (130) Synthesizing unit; (AA) Subject
Abstract translation: 目的：提供一种波束形成方法，一种执行该波束形成方法的装置和一种医学图像系统，以显着减少需要处理的计算量。 构成：波束形成装置（100）包括存储单元（110），加权系数计算单元（120）和合成单元（130）。 存储单元存储从预先测量的回波信号的波束形成系数获得的多个基本向量。 加权因子计算单元通过使用多个存储的基本向量产生应用于从被摄体反射的回波信号的加权因子。 合成单元通过使用多个存储的基本向量将所产生的加权因子应用于从对象反射的回波信号，并且合成应用了加权因子的信号。 （附图标记）（110）存储单元; （120）加权因子计算单位; （130）合成单元; （AA）科目
-
公开(公告)号：KR1020120119787A
公开(公告)日：2012-10-31
申请号：KR1020110037981
申请日：2011-04-22
Applicant: 삼성전자주식회사
CPC classification number: A61B8/5246 , A61B8/08 , A61B8/5207 , G01S15/8977 , G01S15/8997 , A61B8/14 , G01N29/24
Abstract: PURPOSE: A diagnosis image generating method, an apparatus performing the same, a diagnosis system and a medical image system are provided to reduce the amount of calculation by securing the quality of a diagnosis image. CONSTITUTION: A low resolution image signal synthesis unit(110) synthesizes each low resolution image signal. A weight calculating unit(120) calculates weighted value for synthesizing the low resolution image signal. A high resolution image signal synthesis unit(130) applies the calculated weighted value for the low resolution image signal. The high resolution image signal synthesis synthesizes the high resolution image signal through the weighted value. [Reference numerals] (110) Low resolution image signal synthesis unit; (120) Weight calculating unit; (130) High resolution image signal synthesis unit
Abstract translation: 目的：提供诊断图像生成方法，执行该诊断图像的装置，诊断系统和医学图像系统，以通过确保诊断图像的质量来减少计算量。 构成：低分辨率图像信号合成单元（110）合成每个低分辨率图像信号。 权重计算单元（120）计算用于合成低分辨率图像信号的加权值。 高分辨率图像信号合成单元（130）对所计算的低分辨率图像信号的加权值应用。 高分辨率图像信号合成通过加权值合成高分辨率图像信号。 （附图标记）（110）低分辨率图像信号合成单元; （120）重量计算单位; （130）高分辨率图像信号合成单元
-
公开(公告)号：KR1020110034329A
公开(公告)日：2011-04-05
申请号：KR1020090091824
申请日：2009-09-28
Applicant: 삼성전자주식회사
CPC classification number: H04R3/005 , H04R29/004 , H04R2201/401
Abstract: PURPOSE: A gain controlling device and method thereof are provided to adjust bandwidth of a sound signal by using the updated weight. CONSTITUTION: A micro phone array includes at least two microphone which is arranged on the same surface. A frequency converting unit(110) converts a plurality of sound signal received from the microphone array into a signal of each frequency. A weight calculating unit(120) maintains a plurality sound signal which is converted into the frequency area. The weight calculating unit calculates a plurality of sound signal according to the frequency component. A scaling unit(130) adjusts an amplitude of a plurality of acoustic signals by using the calculated weight. The weight calculating unit calculates the weight.
Abstract translation: 目的：提供一种增益控制装置及其方法，以通过使用更新的权重来调整声音信号的带宽。 构成：微电话阵列包括布置在同一表面上的至少两个麦克风。 频率转换单元（110）将从麦克风阵列接收的多个声音信号转换为每个频率的信号。 权重计算单元（120）维持被转换成频率区域的多个声音信号。 权重计算单元根据频率分量来计算多个声音信号。 缩放单元（130）通过使用所计算的权重来调整多个声信号的幅度。 权重计算单元计算权重。
-
公开(公告)号：KR1020100053890A
公开(公告)日：2010-05-24
申请号：KR1020080112734
申请日：2008-11-13
Applicant: 삼성전자주식회사
CPC classification number: G10L21/0208 , G10L2021/02165
Abstract: PURPOSE: A noise eliminating device and a method thereof are provided to eliminate noises effectively in a very short microphone interval by eliminating the noise according to each phase difference by frequency in a noise eliminating unit. CONSTITUTION: A noise estimator(110) estimates a noise signal from a converted frequency domain signal by a frequency converter(100). An amplitude estimator(120) estimates an amplitude of a target sound by frequency through the estimated noise signal. A noise eliminating unit calculates a phase difference by frequency from the amplitude-estimated frequency domain signal. The noise eliminating unit eliminates the noises.
Abstract translation: 目的：提供一种噪声消除装置及其方法，通过在噪声消除单元中根据频率的每个相位差消除噪声，在非常短的麦克风间隔中有效地消除噪声。 构成：噪声估计器（110）通过变频器（100）估计来自转换后的频域信号的噪声信号。 振幅估计器（120）通过估计的噪声信号估计目标声音的频率的频率。 噪声消除单元根据幅度估计频域信号计算出频率的相位差。 噪声消除单元消除噪声。
-
Patent Agency Ranking
公开(公告)号：KR1020090056597A
公开(公告)日：2009-06-03
申请号：KR1020070123818
申请日：2007-11-30
Applicant: 삼성전자주식회사
Abstract: A method and an apparatus for correcting a sound source signal are provided to prevent a distortion of a sound source signal due to characteristic mismatching between individual microphones by correcting the sound source signal according to the calculated reference probability distribution. A probability distribution calculator calculates the probability distributions expressing the number of the sound source signals existing in each interval according to the size interval of the sound source signals. A probability distribution calculator includes an accumulator. The accumulator calculates and accumulates the probability distributions about the size of the sound source signals in each interval. A reference probability distribution calculator(211) calculates the reference probability distribution representing the probability distributions based on the calculated probability distributions. A signal corrector(212) corrects the sound source signals according to the calculated reference probability distribution. The reference probability distribution calculator calculates the reference probability distribution based on the accumulated probability distributions.
Abstract translation: 提供了一种用于校正声源信号的方法和装置，以通过根据所计算的参考概率分布校正声源信号来防止由于各个麦克风之间的特性失配引起的声源信号的失真。 概率分布计算器根据声源信号的大小间隔计算表示存在于每个间隔中的声源信号的数量的概率分布。 概率分布计算器包括累加器。 累加器计算并累加关于每个间隔中声源信号大小的概率分布。 参考概率分布计算器（211）基于计算的概率分布来计算表示概率分布的参考概率分布。 信号校正器（212）根据所计算的参考概率分布校正声源信号。 参考概率分布计算器基于累积的概率分布来计算参考概率分布。
-
公开(公告)号：KR1020090050372A
公开(公告)日：2009-05-20
申请号：KR1020070116763
申请日：2007-11-15
Applicant: 삼성전자주식회사
IPC: G10L21/0208 , G10L15/02 , G10L15/20
CPC classification number: G10K11/178 , G10K2210/108 , G10K2210/1081
Abstract: 본 발명은 혼합 사운드로부터 잡음을 제거하는 방법 및 장치에 관한 것으로, 본 발명에 따른 잡음 제거 방법은 목표 사운드와 잡음을 포함한 음원 신호들을 입력받고, 입력된 음원 신호들로부터 음원 신호들 간의 속성 차이를 나타내는 하나 이상의 특징 벡터를 추출하고, 추출된 특징 벡터에 기초하여 음원 신호들에 대한 잡음 비율을 고려한 감쇄 계수를 산출하며, 산출된 감쇄 계수에 따라 음원 신호들로부터 생성된 출력 신호의 강도를 조절함으로써, 음향 센서를 통해 입력된 혼합 사운드로부터 잡음 신호를 제거하여 선명한 목표 음원 신호를 얻을 수 있다.
-
公开(公告)号：KR100897553B1
公开(公告)日：2009-05-15
申请号：KR1020070001157
申请日：2007-01-04
Applicant: 삼성전자주식회사
CPC classification number: G10L15/22 , G10L2015/227
Abstract: 본 발명은 모바일 기기에서 음성인식 성능을 향상시키기 위한 방법 및 장치에 관한 것으로, 본 발명에 따른 음성 인식 방법은 음성을 입력하는 기기에 대한 사용자의 기기 사용 패턴을 모니터링하고, 모니터링된 결과를 기초로 기기에 저장되어 있는 단어들 중에서 특정 단어들을 선택하여 저장하고, 음향 모델과 특정 단어들을 기초로 음성을 인식함으로써, 사용자가 주로 어디로 전화할지를 예측하여 음성인식에 반영할 수 있으며, 사용자의 기기 이용 패턴을 자동으로 모델링하고 이를 음성인식 대상어휘에 확률적으로 반영하여 음성인식의 체감 성능을 높일 수 있는 효과가 있다.
음성, 인식, 기기, 사용자 단어 모델-
公开(公告)号：KR1020090037845A
公开(公告)日：2009-04-16
申请号：KR1020080129411
申请日：2008-12-18
Applicant: 삼성전자주식회사
Abstract: A method and an apparatus for extracting a target sound signal from a mixed signal are provided to extract a target audio signal in which PESQ(Perceptual Evaluation of Speech Quality) is high from the mixed signal by using an adaptive non-linear filter to an interference noise ratio. A suppressing signal beam former(222) produces a signal in which directivity is suppressed toward a target sound source direction. An emphasizing signal beam forming emphasizes sound pressure with regard to a specific target sound source. A microphone array improves an amplitude by giving proper weight to each signal. A beam former spatially reduces noise of an interference noise signal and a target signal. An adder adds a sound signal inputted through the microphone array. A delay-and-sum algorithm finds out a location of the sound source from a relatively delay time for which a signal reaches to the microphone.
Abstract translation: 提供一种用于从混合信号中提取目标声音信号的方法和装置，通过使用自适应非线性滤波器来提取目标音频信号，其中PESQ（语音质量的感知评估）从混合信号变为高电平 噪音比。 抑制信号光束形成器（222）产生朝向目标声源方向抑制方向性的信号。 强调信号光束形成强调对特定目标声源的声压。 麦克风阵列通过给每个信号赋予适当的重量来改善振幅。 波束形成器在空间上降低干扰噪声信号和目标信号的噪声。 加法器增加通过麦克风阵列输入的声音信号。 延迟和和算法从信号到达麦克风的相对延迟时间中发现声源的位置。
-
公开(公告)号：KR1020080077873A
公开(公告)日：2008-08-26
申请号：KR1020070017620
申请日：2007-02-21
Applicant: 삼성전자주식회사
CPC classification number: G10L15/30
Abstract: A distributed speech recognition system and a method, a terminal and a server for distributed speech recognition are provided to significantly reduce a load of the server by performing detailed matching in a candidate list using a predicted probability value calculated in the terminal. A distributed speech recognition system includes a terminal(110) and a server(150). The terminal decodes an extracted feature vector with respect to an input speech signal into a recognized phoneme row. The server performs a symbol matching for the recognized phoneme row from the terminal and transmits a final recognition result to the terminal. The terminal includes a feature extracting unit(310) extracting the feature vector from the speech signal, a phoneme decoding unit(330) decoding the extracted feature vector into the phoneme row and providing the phoneme row to the server, and a receiving unit receiving the final recognition result from the server.
Abstract translation: 提供一种用于分布式语音识别的分布式语音识别系统和方法，终端和服务器，以通过使用在终端中计算出的预测概率值，在候选列表中进行详细匹配来显着减少服务器的负载。 分布式语音识别系统包括终端（110）和服务器（150）。 终端将提取的特征矢量相对于输入语音信号解码为识别的音素行。 服务器对来自终端的识别音素行执行符号匹配，并向终端发送最终识别结果。 终端包括从语音信号中提取特征向量的特征提取单元（310），将所提取的特征矢量解码为音素行并将音素行提供给服务器的音素解码单元（330），以及接收单元 来自服务器的最终识别结果。
-
-
-
-
-
-
-
-
-
Search Results
220
records
(took 0.032 seconds)
