专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20110232989A1 ESTIMATING A SOUND SOURCE LOCATION USING PARTICLE FILTERING 有权
标题翻译：使用粒子滤波估算声源位置
公开(公告)号：US20110232989A1
公开(公告)日：2011-09-29
申请号：US13133839
申请日：2009-12-11
申请人： Wei Pien Lee , Bahaa Eddine Sarroukh , Leon C. A. Van Stuivenberg , Cornelis Pieter Janse
发明人： Wei Pien Lee , Bahaa Eddine Sarroukh , Leon C. A. Van Stuivenberg , Cornelis Pieter Janse
IPC分类号： G01S3/80
CPC分类号： G01S5/22 , G01S3/8034 , G10L2021/02165 , H04N7/142 , H04N7/147 , H04N7/15 , H04S7/30 , H04S2400/11
摘要： A sound source location is estimated by particle filtering where a set of particles represents a probability density function for a state variable comprising the sound source location. The method includes determining the weight for a particle in response to a correlation between estimated acoustic transfer functions from the sound source to at least two sound recording positions. A weight update function may specifically be determined deterministically from the correlation and thus the correlation may be used as a pseudo-likelihood function for the measurement function of the particle filtering. The acoustic transfer functions may be determined from an audio beamforming towards the sound source. The audio weight may be combined with a video weight to generate a multi-modal particle filtering approach.
摘要翻译：通过粒子滤波来估计声源位置，其中一组粒子表示包括声源位置的状态变量的概率密度函数。该方法包括响应于从声源到至少两个录音位置的估计的声学传递函数之间的相关性来确定颗粒的权重。权重更新功能可以从相关性确定地确定地确定，因此可以将相关性用作用于粒子滤波的测量函数的伪似然函数。声传递函数可以从对声源形成的音频波束确定。音频权重可以与视频权重组合以产生多模式粒子滤波方法。

2. 发明申请

US20110054909A1 LOCALIZING THE POSITION OF A SOURCE OF A VOICE SIGNAL 有权
标题翻译：本地化语音信号源的位置
公开(公告)号：US20110054909A1
公开(公告)日：2011-03-03
申请号：US12990792
申请日：2009-05-05
申请人： Alphons Antonius Maria Lambertus Bruekers , Bahaa Eddine Sarroukh , Thomas Andreas Maria Kevenaar
发明人： Alphons Antonius Maria Lambertus Bruekers , Bahaa Eddine Sarroukh , Thomas Andreas Maria Kevenaar
IPC分类号： G10L21/00 , H04N7/18 , A41D13/00
CPC分类号： G06K9/3216 , G10L15/20 , G10L2015/228
摘要： The invention relates to localizing the position of a person speaking by using pictures of a pattern (21) on an object (20) worn by the person. The object (20) carries a complex pattern (21) that is optimized for determining the orientation of the object (20), the distance from the object to a microphone device (14) and/or to a camera (11). Moreover, the pattern (21) may be arranged for identifying the person carrying the object (20). The determination of the position of the person carrying the object (20) may be used to enhance speech recognition (SR) and/or to provide hands-free voice control of devices (DC), e.g. in hospitals or in industrial settings.
摘要翻译：本发明涉及通过使用由人佩戴的物体（20）上的图案（21）的图片来定位说话人的位置。物体（20）承载经过优化以确定物体（20）的取向，从物体到麦克风装置（14）和/或照相机（11）的距离的复杂图案（21）。此外，图案（21）可以被布置用于识别携带物体（20）的人物。承载对象（20）的人的位置的确定可以用于增强语音识别（SR）和/或提供设备（DC）的免提语音控制，例如，在医院或工业环境中。

3. 发明授权

US08831954B2 Localizing the position of a source of a voice signal 有权
标题翻译：定位语音信号源的位置
公开(公告)号：US08831954B2
公开(公告)日：2014-09-09
申请号：US12990792
申请日：2009-05-05
申请人： Alphons Antonius Maria Lambertus Bruekers , Bahaa Eddine Sarroukh , Thomas Andreas Maria Kevenaar
发明人： Alphons Antonius Maria Lambertus Bruekers , Bahaa Eddine Sarroukh , Thomas Andreas Maria Kevenaar
IPC分类号： G10L21/00 , G10L25/00 , H04R3/00 , G06K9/00 , G06K9/46 , G06K9/32 , G10L15/20
CPC分类号： G06K9/3216 , G10L15/20 , G10L2015/228
摘要： The invention relates to localizing the position of a person speaking by using pictures of a pattern (21) on an object (20) worn by the person. The object (20) carries a complex pattern (21) that is optimized for determining the orientation of the object (20), the distance from the object to a microphone device (14) and/or to a camera (11). Moreover, the pattern (21) may be arranged for identifying the person carrying the object (20). The determination of the position of the person carrying the object (20) may be used to enhance speech recognition (SR) and/or to provide hands-free voice control of devices (DC), e.g. in hospitals or in industrial settings.
摘要翻译：本发明涉及通过使用由人佩戴的物体（20）上的图案（21）的图片来定位说话人的位置。物体（20）承载经过优化以确定物体（20）的取向，从物体到麦克风装置（14）和/或照相机（11）的距离的复杂图案（21）。此外，图案（21）可以被布置用于识别携带物体（20）的人物。承载对象（20）的人的位置的确定可以用于增强语音识别（SR）和/或提供设备（DC）的免提语音控制，例如，在医院或工业环境中。

4. 发明申请

US20110264450A1 SPEECH CAPTURING AND SPEECH RENDERING 有权
标题翻译：语音捕获和语音渲染
公开(公告)号：US20110264450A1
公开(公告)日：2011-10-27
申请号：US13141710
申请日：2009-12-17
申请人： Cornelis Pieter Janse , Leon C.A. Van Stuivenberg , Harm Jan Willem Belt , Bahaa Eddine Sarroukh , Mahdi Triki
发明人： Cornelis Pieter Janse , Leon C.A. Van Stuivenberg , Harm Jan Willem Belt , Bahaa Eddine Sarroukh , Mahdi Triki
IPC分类号： G10L21/02 , G10L21/00
CPC分类号： H04R3/005 , H04M1/6033 , H04M3/56 , H04R2430/20 , H04S7/303 , H04S2400/11
摘要： The invention proposes extracting one or more speech signals (151-154) as well as one or more ambient signals (131) from sound signals captured by microphones, wherein each of the speech signals corresponds to a different speaker. The invention proposes to transmit both the one or more speech signals (151-154) and the one or more ambient signals (131) to a rendering side, as opposed to sending only speech signals. This enables to reproduce the speech and ambient signals in a spatially different way at the rendering side. By reproducing the ambient signals a feeling of “being together” is created. In an embodiment, the invention enables reproducing two or more speech signals spatially from each other and from the ambient signals so that speech intelligibility is increased despite the presence of the ambient signals.
摘要翻译：本发明提出从由麦克风捕获的声音信号中提取一个或多个语音信号（151-154）以及一个或多个环境信号（131），其中每个语音信号对应于不同的扬声器。本发明提出将一个或多个语音信号（151-154）和一个或多个环境信号（131）发送到呈现侧，而不是仅发送语音信号。这使得能够在渲染侧以空间不同的方式再现语音和环境信号。通过再现环境信号，产生“在一起”的感觉。在一个实施例中，本发明使得能够在空间上从环境信号中再现两个或更多个语音信号，使得尽管存在环境信号，语音可懂度也增加。

5. 发明授权

US07764799B2 Audio system providing for filter coefficient copying 失效
标题翻译：提供滤波系数复制的音频系统
公开(公告)号：US07764799B2
公开(公告)日：2010-07-27
申请号：US10596762
申请日：2004-12-20
申请人： David Antoine Christian Marie Roovers , Bahaa Eddine Sarroukh
发明人： David Antoine Christian Marie Roovers , Bahaa Eddine Sarroukh
IPC分类号： H04B3/20
CPC分类号： H04M9/082 , H04R3/005
摘要： A system (1) is described which is suited for suppressing audio distortion. The system comprises echo cancelling means (g1, g2) coupled between an audio output (4) and a distorted desired audio sensing microphone array (3), and a filter arrangement (7) coupled to the echo cancelling means (g1, g2) and/or the microphone array (3). The filter arrangement (7) includes filter coefficients representing at least a part of the audio distortion, such as reverberation. The system also comprises an at least partly mirrored circuit arrangement (g′, 7′) for copying thereby simulated audio distortion representative filter coefficient values into the filter coefficients of said filter arrangement (7). Such copied values can be then used for suppressing reverberation in a distorted desired signal by the filter arrangement (7).
摘要翻译：描述适于抑制音频失真的系统（1）。该系统包括耦合在音频输出（4）和失真的期望音频感测麦克风阵列（3）之间的回波消除装置（g1，g2）以及耦合到回波消除装置（g1，g2）的滤波器装置（7）和 /或麦克风阵列（3）。滤波器装置（7）包括表示音频失真的至少一部分的滤波器系数，例如混响。该系统还包括用于将模拟的音频失真代表滤波器系数值复制到所述滤波器装置（7）的滤波器系数中的至少部分地镜像的电路装置（g'，7'）。这样的复制值然后可以用于通过滤波器装置（7）来抑制失真的期望信号中的混响。

6. 发明申请

US20090003615A1 Audio System Providing For Filter Coefficient Copying 失效
标题翻译：提供滤波器系数复制的音频系统
公开(公告)号：US20090003615A1
公开(公告)日：2009-01-01
申请号：US10596762
申请日：2004-12-20
申请人： David Antoine Roovers , Bahaa Eddine Sarroukh
发明人： David Antoine Roovers , Bahaa Eddine Sarroukh
IPC分类号： H04B3/20
CPC分类号： H04M9/082 , H04R3/005
摘要： A system (1) is described which is suited for suppressing audio distortion. The system comprises echo cancelling means g1, g2 coupled between an audio output (4) and a distorted desired audio sensing microphone array (3), and a filter arrangement (7) coupled to the echo cancelling means g1, g2 and/or the microphone array (3). The filter arrangement (7) includes filter coefficients representing at least a part of the audio distortion, such as reverberation. The system also comprises an at least partly mirrored circuit arrangement g′, 7′ for copying thereby simulated audio distortion representative filter coefficient values into the filter coefficients of said filter arrangement (7). Such copied values can be then used for suppressing reverberation in a distorted desired signal by the filter arrangement (7).
摘要翻译：描述适于抑制音频失真的系统（1）。该系统包括耦合在音频输出（4）和失真的期望音频感测麦克风阵列（3）之间的回波消除装置g1，g2以及耦合到回波消除装置g1，g2和/或麦克风的滤波器装置（7）数组（3）。滤波器装置（7）包括表示音频失真的至少一部分的滤波器系数，例如混响。该系统还包括用于将模拟的音频失真代表性滤波器系数值复制到所述滤波器装置（7）的滤波器系数中的至少部分地镜像的电路装置g'，7'。这样的复制值然后可以用于通过滤波器装置（7）来抑制失真的期望信号中的混响。

7. 发明授权

US08781818B2 Speech capturing and speech rendering 有权
标题翻译：语音捕获和语音渲染
公开(公告)号：US08781818B2
公开(公告)日：2014-07-15
申请号：US13141710
申请日：2009-12-17
申请人： Cornelis Pieter Janse , Leon C. A. Van Stuivenberg , Harm Jan Willem Belt , Bahaa Eddine Sarroukh , Mahdi Triki
发明人： Cornelis Pieter Janse , Leon C. A. Van Stuivenberg , Harm Jan Willem Belt , Bahaa Eddine Sarroukh , Mahdi Triki
IPC分类号： G10L19/00
CPC分类号： H04R3/005 , H04M1/6033 , H04M3/56 , H04R2430/20 , H04S7/303 , H04S2400/11
摘要： The invention proposes extracting one or more speech signals (151-154) as well as one or more ambient signals (131) from sound signals captured by microphones, wherein each of the speech signals corresponds to a different speaker. The invention proposes to transmit both the one or more speech signals (151-154) and the one or more ambient signals (131) to a rendering side, as opposed to sending only speech signals. This enables to reproduce the speech and ambient signals in a spatially different way at the rendering side. By reproducing the ambient signals a feeling of “being together” is created. In an embodiment, the invention enables reproducing two or more speech signals spatially from each other and from the ambient signals so that speech intelligibility is increased despite the presence of the ambient signals.
摘要翻译：本发明提出从由麦克风捕获的声音信号中提取一个或多个语音信号（151-154）以及一个或多个环境信号（131），其中每个语音信号对应于不同的扬声器。本发明提出将一个或多个语音信号（151-154）和一个或多个环境信号（131）发送到呈现侧，而不是仅发送语音信号。这使得能够在渲染侧以空间不同的方式再现语音和环境信号。通过再现环境信号，产生“在一起”的感觉。在一个实施例中，本发明使得能够在空间上从环境信号中再现两个或更多个语音信号，使得尽管存在环境信号，语音可懂度也增加。

8. 发明授权

US08403105B2 Estimating a sound source location using particle filtering 有权
标题翻译：使用粒子滤波估算声源位置
公开(公告)号：US08403105B2
公开(公告)日：2013-03-26
申请号：US13133839
申请日：2009-12-11
申请人： Wei Pien Lee , Bahaa Eddine Sarroukh , Leon C. A. Van Stuivenberg , Cornelis Pieter Janse
发明人： Wei Pien Lee , Bahaa Eddine Sarroukh , Leon C. A. Van Stuivenberg , Cornelis Pieter Janse
IPC分类号： G01S3/80 , G06F17/18
CPC分类号： G01S5/22 , G01S3/8034 , G10L2021/02165 , H04N7/142 , H04N7/147 , H04N7/15 , H04S7/30 , H04S2400/11
摘要： A sound source location is estimated by particle filtering where a set of particles represents a probability density function for a state variable comprising the sound source location. The method includes determining the weight for a particle in response to a correlation between estimated acoustic transfer functions from the sound source to at least two sound recording positions. A weight update function may specifically be determined deterministically from the correlation and thus the correlation may be used as a pseudo-likelihood function for the measurement function of the particle filtering. The acoustic transfer functions may be determined from an audio beamforming towards the sound source. The audio weight may be combined with a video weight to generate a multi-modal particle filtering approach.
摘要翻译：通过粒子滤波来估计声源位置，其中一组粒子表示包括声源位置的状态变量的概率密度函数。该方法包括响应于从声源到至少两个录音位置的估计的声学传递函数之间的相关性来确定颗粒的权重。权重更新功能可以从相关性确定地确定地确定，因此可以将相关性用作用于粒子滤波的测量函数的伪似然函数。声传递函数可以从对声源形成的音频波束确定。音频权重可以与视频权重组合以产生多模式粒子滤波方法。

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