-
71.发明授权SIGNAL SEPARATOR, METHOD FOR DETERMINING OUTPUT SIGNALS ON THE BASIS OF MICROPHONE SIGNALS, AND COMPUTER PROGRAM 有权SIGNAL BREAKER，方法确定输出SIGNALS基于麦克风信号和计算机程序
公开(公告)号：EP2027581B1
公开(公告)日：2012-02-29
申请号：EP07764622.2
申请日：2007-06-12
CPC分类号： G10L21/028 , G10L21/0272 , H04R3/005
摘要： A signal separator (100) for determining a first output signal (a1) describing an audio content of a useful-signal source in a first microphone signal, and for determining a second output (a2) signal describing an audio content of the useful-signal source in a second microphone signal comprises a source separator (130) for receiving the two microphone signals and for separating audio contents of at least two signal sources. The source separator (130) is designed to obtain a first partial signal (y1) essentially describing an audio content of a first signal source, and representing the first output signal, and so as to obtain a second partial signal essentially (y2) describing an audio content of a second signal source. The source separator (130) is designed to adjust parameters of a processing specification for generating the first partial signal from the microphone signal in such a manner that a distortion of the first partial signal relative to the first microphone signal is smaller than a maximum distortion, and to adjust parameters of a processing specification for generating the second partial signal from the microphone signals in such a manner that a distortion of the second partial signal relative to the second microphone signal is smaller than a maximum distortion. The signal separator further includes a signal remover for removing the second partial signal from the second microphone signal so as to obtain the second output signal, wherein the second partial signal is reduced. The signal separator offers the advantage that a multi-channel representation of the microphone signals which is corrected in terms of an interference signal may be achieved in a particularly simple manner by using a secondary condition in the source separator.
-
72.发明公开METHOD AND DEVICE FOR GENERATING, PLAYING AUDIO SIGNALS, AND PROCESSING SYSTEM FOR AUDIO SIGNALS 有权VERFAHREN UND VORRICHTUNG ZUR ERZEUGUNG VON TONSIGNALEN
公开(公告)号：EP2323425A1
公开(公告)日：2011-05-18
申请号：EP09809218.2
申请日：2009-08-21
发明人： ZHAN, Wuzhou , WANG, Dongqi
IPC分类号： H04S3/00
CPC分类号： H04S7/30 , G10L19/008 , G10L21/028 , G10L2021/02166 , H04N7/147 , H04N7/15 , H04N13/239 , H04N13/271 , H04N13/30 , H04R1/403 , H04R1/406 , H04R2203/12 , H04S2400/11 , H04S2400/15 , H04S2420/03
摘要： A method for generating and playing audio signals and a system for processing audio signals are disclosed. The method for generating audio signals includes: generating distance information about an audio signal corresponding to a view point position, according to obtained auxiliary video and direction information about the audio signal, where the auxiliary video is a disparity map or a depth map; encoding the direction information and distance information about the audio signal, and sending the encoded information. The apparatus for generating audio signals includes an audio signal distance information obtaining module and an audio signal encoding module. With the present invention, the position information, including direction information and distance information, about the audio signal may be obtained accurately in combination with a three-dimensional video signal and a three-dimensional audio signal, without increasing the size of a microphone array, and the audio signal is sent and played.
摘要翻译： 公开了一种用于产生和播放音频信号的方法以及用于处理音频信号的系统。 用于产生音频信号的方法包括：根据获得的辅助视频和关于音频信号的方向信息，生成与视点位置相对应的音频信号的距离信息，其中辅助视频是视差图或深度图; 编码关于音频信号的方向信息和距离信息，以及发送编码信息。 用于产生音频信号的装置包括音频信号距离信息获取模块和音频信号编码模块。 利用本发明，可以在不增加麦克风阵列的尺寸的情况下，与三维视频信号和三维音频信号相结合地准确地获得关于音频信号的方向信息和距离信息的位置信息， 音频信号被发送和播放。
-
73.发明公开ENHANCED BLIND SOURCE SEPARATION ALGORITHM FOR HIGHLY CORRELATED MIXTURES 有权VERBESSERTER BLINDQUELLEN-SEPARATIONSALGORITHMUSFÜRHOCHKORRELIERTE MISCHUNGEN
公开(公告)号：EP2245861A1
公开(公告)日：2010-11-03
申请号：EP09706217.8
申请日：2009-01-29
CPC分类号： G10L21/028 , G10L2021/02166 , H04R3/005 , H04R25/40
摘要： An enhanced blind source separation technique is provided to improve separation of highly correlated signal mixtures. A beamforming algorithm is used to precondition correlated first and second input signals in order to avoid indeterminacy problems typically associated with blind source separation. The beamforming algorithm may apply spatial filters to the first signal and second signal in order to amplify signals from a first direction while attenuating signals from other directions. Such directionality may serve to amplify a desired speech signal in the first signal and attenuate the desired speech signal from the second signal. Blind source separation is then performed on the beamformer output signals to separate the desired speech signal and the ambient noise and reconstruct an estimate of the desired speech signal. To enhance the operation of the beamformer and/or blind source separation, calibration may be performed at one or more stages.
摘要翻译： 提供增强的盲源分离技术来改善高度相关的信号混合物的分离。 波束形成算法用于预处理相关的第一和第二输入信号，以避免通常与盲源分离相关联的不确定性问题。 波束形成算法可以对第一信号和第二信号应用空间滤波器，以便在衰减来自其它方向的信号的同时放大来自第一方向的信号。 这样的方向性可以用于在第一信号中放大期望的语音信号，并从第二信号中衰减所需的语音信号。 然后对波束形成器输出信号执行盲源分离，以分离所需的语音信号和环境噪声，并重构所需语音信号的估计。 为了增强波束形成器和/或盲源分离的操作，可以在一个或多个阶段执行校准。
-
74.发明公开SIGNAL SEPARATOR, METHOD FOR DETERMINING OUTPUT SIGNALS ON THE BASIS OF MICROPHONE SIGNALS, AND COMPUTER PROGRAM 有权SIGNAL BREAKER，方法确定输出SIGNALS基于麦克风信号和计算机程序
公开(公告)号：EP2027581A1
公开(公告)日：2009-02-25
申请号：EP07764622.2
申请日：2007-06-12
CPC分类号： G10L21/028 , G10L21/0272 , H04R3/005
摘要： A signal separator (100) for determining a first output signal (a1) describing an audio content of a useful-signal source in a first microphone signal, and for determining a second output (a2) signal describing an audio content of the useful-signal source in a second microphone signal comprises a source separator (130) for receiving the two microphone signals and for separating audio contents of at least two signal sources. The source separator (130) is designed to obtain a first partial signal (y1) essentially describing an audio content of a first signal source, and representing the first output signal, and so as to obtain a second partial signal essentially (y2) describing an audio content of a second signal source. The source separator (130) is designed to adjust parameters of a processing specification for generating the first partial signal from the microphone signal in such a manner that a distortion of the first partial signal relative to the first microphone signal is smaller than a maximum distortion, and to adjust parameters of a processing specification for generating the second partial signal from the microphone signals in such a manner that a distortion of the second partial signal relative to the second microphone signal is smaller than a maximum distortion. The signal separator further includes a signal remover for removing the second partial signal from the second microphone signal so as to obtain the second output signal, wherein the second partial signal is reduced. The signal separator offers the advantage that a multi-channel representation of the microphone signals which is corrected in terms of an interference signal may be achieved in a particularly simple manner by using a secondary condition in the source separator.
-
75.发明公开Method and apparatus for separating a sound-source signal and method and device for detecting pitch 有权的方法和装置，用于确定基本频率分离的声源信号和方法及装置
公开(公告)号：EP1566796A3
公开(公告)日：2005-10-26
申请号：EP05250692.0
申请日：2005-02-08
申请人： SONY CORPORATION
CPC分类号： G10L21/0272 , G10L21/028 , G10L25/90
摘要： A sound-source signal separating method including steps of enhancing a target sound-source signal in an input audio signal, the input audio signal being from a mixture of acoustic signals from a plurality of sound sources and picked up by a plurality of sound pickup devices, detecting a pitch of the target sound-source signal in the input audio signal, and separating the target sound-signal from the input audio signal based on the detected pitch and the sound-source signal enhanced in the sound-source signal enhancing step.
-
76.发明公开METHOD AND SYSTEM FOR SEPARATING PLURALITY OF ACOUSTIC SIGNALS GENERATED BY PLURALITY OF ACOUSTIC SOURCES 有权方法和系统分离而产生BY声源多数成员的几种声音信号
公开(公告)号：EP1568013A1
公开(公告)日：2005-08-31
申请号：EP03789598.4
申请日：2003-12-11
IPC分类号： G10L21/02
CPC分类号： G10L21/028
摘要： A method separates acoustic signals generated by multiple acoustic sources, such as mixed speech spoken simultaneously by several speakers (101,102) in the same room. For each source, the acoustic signals are combined into a mixed signal acquired by multiple microphones (110), at least one for each source. The mixed signal is filtered, and the filtered signals are summed into a signal (131) from which features are extracted. A target sequence (151) through a factorial HMM is estimated, and filter parameters (161) are optimized accordingly. These steps are repeated until the filter parameters converge to optimal filtering parameters, which are then used to filter the mixed signal once more, and the summed output of this last filtering is the acoustic signal for a particular acoustic source.
-
77.发明授权Method and system for recognizing, indexing, and searching acoustic signals 有权一种用于识别，索引和搜索的声信号的方法和系统
公开(公告)号：EP1260968B1
公开(公告)日：2005-03-30
申请号：EP02010724.9
申请日：2002-05-14
发明人： Casey, Michael A.
CPC分类号： G10L21/028 , G06F17/30743 , G10L15/02 , G10L15/142
-
公开(公告)号：EP1160772A3
公开(公告)日：2004-01-14
申请号：EP01304801.2
申请日：2001-05-31
IPC分类号： G10L21/02
CPC分类号： G10L21/028 , G10L2021/02166 , H04R3/005 , H04R2201/403
摘要： A signal processing system is provided which includes one or more receivers for receiving signals generated by a plurality of signal sources. The system has a memory for storing a predetermined function which gives, for a set of input signal values, a probability density for parameters of a respective signal model which is assumed to have generated the signals in the received signal values. The system applies a set of received signal values to the stored function to generate the probability density function and then draws samples from it. The system then analyses the drawn samples to determine parameter values representative of the signal from at least one of the sources.
-
79.发明公开Method and system for recognizing, indexing, and searching acoustic signals 有权Verfahren und System zum Erkennen，Indizieren und Suchen von akustischen Signalen
公开(公告)号：EP1260968A1
公开(公告)日：2002-11-27
申请号：EP02010724.9
申请日：2002-05-14
发明人： Casey, Michael A.
CPC分类号： G10L21/028 , G06F17/30743 , G10L15/02 , G10L15/142
摘要： A computerized method extracts features from an acoustic signal generated from one or more sources. The acoustic signal are first windowed and filtered to produce a spectral envelope for each source. The dimensionality of the spectral envelope is then reduced to produce a set of features for the acoustic signal. The features in the set are clustered to produce a group of features for each of the sources. The features in each group include spectral features and corresponding temporal features characterizing each source. Each group of features is a quantitative descriptor that is also associated with a qualitative descriptor. Hidden Markov models are trained with sets of known features and stored in a database. The database can then be indexed by sets of unknown features to select or recognize like acoustic signals.
摘要翻译： 计算机化方法从由一个或多个源产生的声信号中提取特征。 声信号首先被窗口化并被过滤以产生每个源的频谱包络。 然后减小频谱包络的维数以产生用于声信号的一组特征。 集合中的功能集群，以为每个源生成一组功能。 每个组中的特征包括光谱特征和表征每个源的对应的时间特征。 每组特征是定量描述符，也与定性描述符相关联。 隐藏的马尔科夫模型训练有一组已知功能并存储在数据库中。 然后可以通过一组未知特征来索引数据库，以选择或识别像声信号。
-
公开(公告)号：EP0339891B1
公开(公告)日：1995-04-05
申请号：EP89304017.0
申请日：1989-04-21
发明人： Miyamae, Koichi , Omata, Satoshi
IPC分类号： G10L3/00
CPC分类号： G10L21/028 , G10L25/18
-
-
-
-
-
-
-
-
-
搜索结果
111 条记录 (耗时 0.019 秒)
