公开(公告)号：US20080033723A1

公开(公告)日：2008-02-07

申请号：US11882444

申请日：2007-08-01

申请人： Giljin Jang ,  Jeongsu Kim ,  John Bridle ,  Melvyn Hunt

发明人： Giljin Jang ,  Jeongsu Kim ,  John Bridle ,  Melvyn Hunt

IPC分类号： G10L15/00

CPC分类号： G10L25/78 ,  G10L15/04

摘要： A speech recognition method, medium, and system. The method includes detecting an energy change of each frame making up signals including speech and non-speech signals, and identifying a speech segment corresponding to frames that include only speech signals from among the frames based inclusive of the detected energy change.

摘要翻译： 语音识别方法，媒介和系统。 该方法包括检测构成包括语音和非语音信号的信号的每个帧的能量变化，以及识别与包括检测到的能量变化在内的帧之间仅包括语音信号的帧相对应的语音段。

公开(公告)号：US20070185711A1

公开(公告)日：2007-08-09

申请号：US11346273

申请日：2006-02-03

申请人： Giljin Jang ,  Jeongsu Kim ,  Kwangcheol Oh ,  Sungcheol Kim

发明人： Giljin Jang ,  Jeongsu Kim ,  Kwangcheol Oh ,  Sungcheol Kim

IPC分类号： G10L21/02

CPC分类号： G10L21/0208

摘要： A speech enhancement apparatus and method and a computer-readable recording medium having a program recorded thereon execute a speech enhancement method. The speech enhancement apparatus includes a spectrum subtraction unit generating a subtracted spectrum by subtracting an estimated noise spectrum from a received speech spectrum, a correction function modeling unit generating a correction function to minimize a noise spectrum using variation of a noise spectrum included in training data, and a spectrum correction unit generating a corrected spectrum by correcting the subtracted spectrum using the correction function.

摘要翻译： 具有记录在其上的程序的语音增强装置和方法以及计算机可读记录介质执行语音增强方法。 语音增强装置包括：频谱减法单元，从接收到的语音频谱中减去估计的噪声频谱，生成减法频谱;校正函数建模单元，生成校正函数，使训练数据中包含的噪声频谱的变化最小化噪声谱; 以及频谱校正单元，通过使用校正函数校正所述减去的频谱来生成校正的频谱。

公开(公告)号：US09009048B2

公开(公告)日：2015-04-14

申请号：US11882444

申请日：2007-08-01

申请人： Giljin Jang ,  Jeongsu Kim ,  John S. Bridle ,  Melvyn J. Hunt

发明人： Giljin Jang ,  Jeongsu Kim ,  John S. Bridle ,  Melvyn J. Hunt

IPC分类号： G10L15/04 ,  G10L15/02 ,  G10L15/00 ,  G10L21/00 ,  G10L25/78

CPC分类号： G10L25/78 ,  G10L15/04

摘要： A speech recognition method, medium, and system. The method includes detecting an energy change of each frame making up signals including speech and non-speech signals, and identifying a speech segment corresponding to frames that include only speech signals from among the frames based on the detected energy change.

摘要翻译： 语音识别方法，媒介和系统。 该方法包括检测构成包括语音和非语音信号的信号的每个帧的能量变化，并且基于检测到的能量变化来识别对应于来自帧中的来自帧的语音信号的帧的语音段。

公开(公告)号：US08214205B2

公开(公告)日：2012-07-03

申请号：US11346273

申请日：2006-02-03

申请人： Giljin Jang ,  Jeongsu Kim ,  Kwangcheol Oh ,  Sungcheol Kim

发明人： Giljin Jang ,  Jeongsu Kim ,  Kwangcheol Oh ,  Sungcheol Kim

IPC分类号： G10L21/02 ,  G10L19/14 ,  G10L15/00 ,  G10L15/20 ,  G10L19/00

CPC分类号： G10L21/0208

摘要： A speech enhancement apparatus and method and a computer-readable recording medium having a program recorded thereon execute a speech enhancement method. The speech enhancement apparatus includes a spectrum subtraction unit generating a subtracted spectrum by subtracting an estimated noise spectrum from a received speech spectrum, a correction function modeling unit generating a correction function to minimize a noise spectrum using variation of a noise spectrum included in training data, and a spectrum correction unit generating a corrected spectrum by correcting the subtracted spectrum using the correction function.

摘要翻译： 具有记录在其上的程序的语音增强装置和方法以及计算机可读记录介质执行语音增强方法。 语音增强装置包括：频谱减法单元，从接收到的语音频谱中减去估计的噪声频谱，生成减法频谱;校正函数建模单元，生成校正函数，使训练数据中包含的噪声频谱的变化最小化噪声谱; 以及频谱校正单元，通过使用校正函数校正所述减去的频谱来生成校正的频谱。

公开(公告)号：US20060034361A1

公开(公告)日：2006-02-16

申请号：US11202025

申请日：2005-08-12

申请人： Changkyu Choi ,  Giljin Jang

发明人： Changkyu Choi ,  Giljin Jang

IPC分类号： H04B17/00

CPC分类号： H04R5/04 ,  G10L19/008 ,  G10L21/0272 ,  H04B17/345

摘要： A method and apparatus for eliminating cross-channel interference, and a multi-channel source separation method and a multi-channel source separation apparatus using the same. The multi-channel source signal separation apparatus includes: a source separation unit separating multi-channel source signals from a mixture including the multi-channel source signals; and a post-processing unit eliminating cross-channel interference from an arbitrary channel output of the separated multi-channel source signals by using an interference elimination coefficient determined based on a degree of interference between the arbitrary channel output and a different channel output of the separated multi-channel source signals.

摘要翻译： 一种用于消除交叉信道干扰的方法和装置，以及多信道源分离方法和使用该方法的多信道源分离装置。 多信道源信号分离装置包括：源分离单元，从包括多信道源信号的混合分离多信道源信号; 以及后处理单元，通过使用基于任意信道输出与所分离的多信道源信号的不同信道输出之间的干扰程度确定的干扰消除系数来消除来自分离的多信道源信号的任意信道输出的交叉信道干扰 多通道源信号。

公开(公告)号：US08200484B2

公开(公告)日：2012-06-12

申请号：US11202025

申请日：2005-08-12

申请人： Changkyu Choi ,  Giljin Jang

发明人： Changkyu Choi ,  Giljin Jang

IPC分类号： G10L21/02 ,  G10L11/02

CPC分类号： H04R5/04 ,  G10L19/008 ,  G10L21/0272 ,  H04B17/345

摘要： Cross-channel interference is eliminated and multi-channel sources are separated by estimating a source absence probability for a current frame of a first channel output, and determining an interference elimination coefficient for matching a secondary signal of the first channel output with a primary signal of a second channel output by using the source absence probability, generating an interference signal by multiplying the second channel output by an over-subtraction factor and the interference elimination coefficient, wherein a partial differentiation is performed for a v-norm value of a spectral amplitude difference, between the first channel output and the second channel output multiplied by the interference elimination coefficient and a result of multiplication of the source absence probability, by using the interference elimination coefficient to determine an update amount of the interference elimination coefficient for a next frame.

摘要翻译： 消除了跨信道干扰，并且通过估计第一信道输出的当前帧的源缺失概率来分离多信道源，并且确定用于将第一信道输出的辅信号与第一信道输出的辅信号匹配的干扰消除系数与 通过使用源不存在概率输出第二通道，通过将第二通道输出乘以过减去系数和干扰消除系数来产生干扰信号，其中对频谱幅度差的v-范数值执行偏微分 通过使用干扰消除系数来确定下一帧的干扰消除系数的更新量，在第一信道输出和第二信道输出乘以干扰消除系数和源缺失概率相乘的结果之间。