专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

US20100119079A1 APPRATUS AND METHOD FOR PREVENTING NOISE 有权
标题翻译：防止噪音的方法和方法
公开(公告)号：US20100119079A1
公开(公告)日：2010-05-13
申请号：US12612857
申请日：2009-11-05
申请人： Kyu-hong KIM , Kwang-cheol Oh
发明人： Kyu-hong KIM , Kwang-cheol Oh
IPC分类号： H04B15/00
CPC分类号： G10L21/0208 , G10L2021/02165
摘要： Provided are an apparatus and method for preventing noise. The apparatus estimates a noise signal from a signal transformed into a frequency domain, uses the estimated noise signal to estimate the amplitude of the frequency-domain signal according to a frequency band, and then calculates a phase difference according to a frequency band and eliminates or prevents noise from the amplitude-estimated frequency-domain signal based on the calculated phase difference according frequency band.
摘要翻译：提供了一种用于防止噪声的装置和方法。该装置从变换为频域的信号估计噪声信号，使用估计噪声信号根据频带估计频域信号的振幅，然后根据频带计算相位差，消除或基于计算出的相位差根据频带来防止来自振幅估计频域信号的噪声。

22. 发明授权

US07711558B2 Apparatus and method for detecting voice activity period 有权
标题翻译：检测语音活动期的装置和方法
公开(公告)号：US07711558B2
公开(公告)日：2010-05-04
申请号：US11472304
申请日：2006-06-22
申请人： Gil-jin Jang , Jeong-su Kim , Kwang-cheol Oh
发明人： Gil-jin Jang , Jeong-su Kim , Kwang-cheol Oh
IPC分类号： G10L21/02
CPC分类号： G10L25/78
摘要： An apparatus and method for detecting a voice activity period. The apparatus for detecting a voice activity period includes a domain conversion module that converts an input signal into a frequency domain signal in the unit of a frame obtained by dividing the input signal at predetermined intervals, a subtracted-spectrum-generation module that generates a spectral subtraction signal which is obtained by subtracting a predetermined noise spectrum from the converted frequency domain signal, a modeling module that applies the spectral subtraction signal to a predetermined probability distribution model, and a speech-detection module that determines whether a speech signal is present in a current frame through a probability distribution calculated by the modeling module.
摘要翻译：一种用于检测语音活动期的装置和方法。用于检测语音活动期间的装置包括域转换模块，该域转换模块将输入信号转换成以预定间隔划分输入信号所获得的帧为单位的频域信号;产生频谱的减法频谱生成模块通过从转换的频域信号中减去预定的噪声频谱获得的减法信号，将频谱减法信号应用于预定概率分布模型的建模模块，以及确定语音信号是否存在于语音信号中的语音检测模块通过由建模模块计算出的概率分布的当前帧。

23. 发明申请

US20070174048A1 Method and apparatus for detecting pitch by using spectral auto-correlation 有权
标题翻译：使用频谱自相关检测音调的方法和装置
公开(公告)号：US20070174048A1
公开(公告)日：2007-07-26
申请号：US11604272
申请日：2006-11-27
申请人： Kwang Cheol Oh , Jae-Hoon Jeong
发明人： Kwang Cheol Oh , Jae-Hoon Jeong
IPC分类号： G10L11/04
CPC分类号： G10L25/90
摘要： A method and an apparatus for detecting a pitch in input voice signals by using a spectral auto-correlation. The pitch detection method includes: performing a Fourier transform on the input voice signals after performing a pre-processing on the input voice signals, performing an interpolation on the transformed voice signals, calculating a spectral difference from a difference between spectrums of the interpolated voice signals, calculating a spectral auto-correlation by using the calculated spectral difference, determining a voicing region based on the calculated spectral auto-correlation, and extracting a pitch by using the spectral auto-correlation corresponding to the voicing region.
摘要翻译：一种用于通过使用频谱自相关来检测输入语音信号中的音调的方法和装置。音调检测方法包括：对输入的语音信号进行预处理后对输入的语音信号进行傅里叶变换，对变换后的语音信号进行插值，根据插入的语音信号的频谱之差计算频谱差通过使用计算出的频谱差计算频谱自相关，基于所计算的频谱自相关来确定语音区域，以及通过使用与发音区域对应的频谱自相关来提取音调。

24. 发明授权

US08693704B2 Method and apparatus for canceling noise from mixed sound 有权
标题翻译：从混合声音中消除噪音的方法和装置
公开(公告)号：US08693704B2
公开(公告)日：2014-04-08
申请号：US12078551
申请日：2008-04-01
申请人： Kyu-hong Kim , Kwang-cheol Oh , Jae-hoon Jeong , So-young Jeong
发明人： Kyu-hong Kim , Kwang-cheol Oh , Jae-hoon Jeong , So-young Jeong
IPC分类号： H04B15/00 , G10K11/16 , A61F11/06
CPC分类号： G10K11/178 , G10K2210/108 , G10K2210/1081
摘要： A method, medium, and apparatus canceling noise from a mixed sound. The method includes receiving sound source signals including a target sound and noise, extracting at least one feature vector indicating an attribute difference between the sound source signals from the sound source signals, calculating a suppression coefficient considering ratios of noise to the sound source signals based on the at least one extracted feature vector, and canceling the sound source signals corresponding to noise by controlling an intensity of an output signal generated from the sound source signals according to the calculated suppression coefficient. Accordingly, a clear target sound source signal can be obtained.
摘要翻译：一种从混合声音中消除噪声的方法，介质和装置。该方法包括接收包括目标声音和噪声的声源信号，从声源信号中提取表示声源信号之间的属性差异的至少一个特征向量，基于噪声与声源信号的比率计算抑制系数，基于所述至少一个提取的特征向量，并且通过根据所计算的抑制系数控制从所述声源信号产生的输出信号的强度来抵消对应于噪声的声源信号。因此，可以获得清晰的目标声源信号。

25. 发明授权

US08311811B2 Method and apparatus for detecting pitch by using subharmonic-to-harmonic ratio 有权
标题翻译：通过使用次和谐谐波比来检测音调的方法和装置
公开(公告)号：US08311811B2
公开(公告)日：2012-11-13
申请号：US11604276
申请日：2006-11-27
申请人： Kwang Cheol Oh , Jae-Hoo Jeong
发明人： Kwang Cheol Oh , Jae-Hoo Jeong
IPC分类号： G10L11/04
CPC分类号： G10L25/90
摘要： A method and an apparatus for detecting a pitch in input voice signals by using a subharmonic-to-harmonic ratio (SHR). The pitch detection method includes performing a Fourier transform on the input voice signals after performing a pre-processing on the input voice signals, performing an interpolation on the transformed voice signals, calculating a normalized local center of gravity (NLCG) on a spectrum of the interpolated voice signals, calculating a cumulated sum of the calculated NLCG, calculating an SHR from the spectrum based on the calculated cumulated sum, and extracting the pitch based on the calculated SHR.
摘要翻译：一种用于通过使用次谐波 - 谐波比（SHR）来检测输入语音信号中的音调的方法和装置。音调检测方法包括：在对输入的语音信号进行预处理之后对输入的语音信号执行傅里叶变换，对变换的语音信号执行插值，在频谱上计算归一化的局部重心（NLCG）内插语音信号，计算所计算的NLCG的累积和，基于所计算的累积和从频谱计算SHR，以及基于所计算的SHR提取音高。

26. 发明授权

US08229129B2 Method, medium, and apparatus for extracting target sound from mixed sound 有权
标题翻译：用于从混合声音提取目标声音的方法，介质和装置
公开(公告)号：US08229129B2
公开(公告)日：2012-07-24
申请号：US12078942
申请日：2008-04-08
申请人： So-young Jeong , Kwang-cheol Oh , Jae-hoon Jeong , Kyu-hong Kim
发明人： So-young Jeong , Kwang-cheol Oh , Jae-hoon Jeong , Kyu-hong Kim
IPC分类号： H04R3/02
CPC分类号： H04R3/005
摘要： A method, medium, and apparatus for extracting a target sound from mixed sound. The method includes receiving a mixed signal through a microphone array, generating a first signal whose directivity is emphasized toward a target sound source and a second signal whose directivity toward the target sound source is suppressed based on the mixed signal, and extracting a target sound signal from the first signal by masking an interference sound signal, which is contained in the first signal, based on a ratio of the first signal to the second signal. Therefore, a target sound signal can be clearly separated from a mixed sound signal which contains a plurality of sound signals and is input to a microphone array.
摘要翻译：一种用于从混合声音提取目标声音的方法，介质和装置。该方法包括通过麦克风阵列接收混合信号，产生朝向目标声源强调方向性的第一信号和基于混合信号抑制对目标声源的方向性的第二信号，并且提取目标声音信号基于第一信号与第二信号的比率，通过屏蔽包含在第一信号中的干扰声音信号从第一信号中获取信号。因此，可以将目标声音信号与包含多个声音信号的混合声音信号清楚地分离并输入到麦克风阵列。

27. 发明授权

US08213263B2 Apparatus and method of detecting target sound 有权
标题翻译：检测目标声音的装置和方法
公开(公告)号：US08213263B2
公开(公告)日：2012-07-03
申请号：US12469557
申请日：2009-05-20
申请人： Kyu-hong Kim , Kwang-cheol Oh
发明人： Kyu-hong Kim , Kwang-cheol Oh
IPC分类号： G01S3/80
CPC分类号： G01S3/8083
摘要： An apparatus and method of voice activity detection (VAD) are disclosed. To detect a target sound, a target sound detecting apparatus calculates the phase difference corresponding to each frequency component from a plurality of sound signals converted in frequency domain, calculates a characteristic value indicating possibility that the phase difference of the frequency component is within an allowable phase difference range of target sound calculated based on a direction angle of the target sound, and detects the presence and/or absence of target sound using the characteristic value.
摘要翻译：公开了语音活动检测（VAD）的装置和方法。为了检测目标声音，目标声音检测装置从频域转换的多个声音信号中计算出与各频率成分对应的相位差，计算表示频率分量的相位差处于容许相位的可能性的特性值基于目标声音的方向角度计算的目标声音的差异范围，并且使用该特征值来检测目标声音的存在和/或不存在。

28. 发明授权

US08160270B2 Method and apparatus for acquiring multi-channel sound by using microphone array 有权
标题翻译：使用麦克风阵列获取多声道声音的方法和装置
公开(公告)号：US08160270B2
公开(公告)日：2012-04-17
申请号：US12076119
申请日：2008-03-13
申请人： Kwang-cheol Oh , Jae-hoon Jeong , Kyu-hong Kim , So-young Jeong
发明人： Kwang-cheol Oh , Jae-hoon Jeong , Kyu-hong Kim , So-young Jeong
IPC分类号： H04R3/00
CPC分类号： H04R1/406 , H04R3/005 , H04R2430/20 , H04S3/008 , H04S2400/15
摘要： Provided are a method and an apparatus for acquiring a multi-channel sound by using a microphone array. The method estimates positions of sound sources corresponding to sound source signals, which are mixed together, from the sound source signals input via a microphone array; and generates a multi-channel sound source signal by compensating for the sound source signals, based on differences between the estimated positions of the sound sources and a position of a virtual microphone array substituting for the microphone array. By doing so, the multi-channel sound having a stereoscopic effect can be acquired from a plurality of distant sound source signals which are input via the microphone array from a portable sound acquisition device.
摘要翻译：提供了一种通过使用麦克风阵列获取多声道声音的方法和装置。该方法从通过麦克风阵列输入的声源信号估计对应于混合在一起的声源信号的声源的位置; 并且基于声源的估计位置与代替麦克风阵列的虚拟麦克风阵列的位置之间的差异来补偿声源信号来产生多声道声源信号。通过这样做，可以从便携式声音获取装置经由麦克风阵列输入的多个远程声源信号中获得具有立体效果的多声道声音。

29. 发明申请

US20110051956A1 APPARATUS AND METHOD FOR REDUCING NOISE USING COMPLEX SPECTRUM 审中-公开
标题翻译：使用复杂光谱降低噪声的装置和方法
公开(公告)号：US20110051956A1
公开(公告)日：2011-03-03
申请号：US12862026
申请日：2010-08-24
申请人： So-Young JEONG , Kyu-Hong KIM , Kwang-Cheol OH , Jae-Hong JEONG
发明人： So-Young JEONG , Kyu-Hong KIM , Kwang-Cheol OH , Jae-Hong JEONG
IPC分类号： H04B15/00
CPC分类号： G10L21/0208 , G10L2021/02165
摘要： An apparatus and method reduce noise in a complex spectrum domain to extract a target signal from input signals containing noise and target speech. Noise estimation may be performed through a filter with a filter learning coefficient that is updated according to a prior-signal-to-noise ratio (prior-SNR). Also, noise estimation accuracy may be improved by using confidential weighted scores. The target signal may be extracted by representing candidates of the target signal as at least two circles in the complex spectrum domain using the estimated noise and then geometrically calculating the intersections of the circles.
摘要翻译：一种降低复杂频域噪声的装置和方法，从包含噪声和目标语音的输入信号中提取目标信号。可以通过具有根据先前信噪比（先前SNR）更新的滤波器学习系数的滤波器来执行噪声估计。此外，可以通过使用机密加权分数来提高噪声估计精度。可以通过使用估计的噪声将复合频域中的至少两个圆表示目标信号的候选，然后几何计算圆的交点来提取目标信号。

30. 发明申请

US20100254539A1 APPARATUS AND METHOD FOR EXTRACTING TARGET SOUND FROM MIXED SOURCE SOUND 审中-公开
标题翻译：从混合源声音提取目标声音的装置和方法
公开(公告)号：US20100254539A1
公开(公告)日：2010-10-07
申请号：US12754990
申请日：2010-04-06
申请人： So-young JEONG , Kwang-cheol Oh , Jae-hoon Jeong , Kyu-hong Kim
发明人： So-young JEONG , Kwang-cheol Oh , Jae-hoon Jeong , Kyu-hong Kim
IPC分类号： H04R29/00 , H04B15/00
CPC分类号： G10L21/0272
摘要： A technology for eliminating or reducing interference sound from a sound signal to extract target sound is provided. Interference sound is modeled using training noise, and mixed source sound is separated using the modeled interference sound. The mixed source sound is separated into target sound and interference sound using a basis matrix of the modeled interference sound.
摘要翻译：提供了用于消除或减少来自声音信号的干扰声音以提取目标声音的技术。使用训练噪声对干扰声进行建模，并使用模拟干扰声分离混合声源。混合源声音使用建模干扰声的基矩阵分离为目标声音和干扰声音。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式