公开(公告)号：EP3223253A1

公开(公告)日：2017-09-27

申请号：EP16305325.9

申请日：2016-03-23

申请人： Thomson Licensing

发明人： GILBERTON, Philippe ,  DUONG, Quang Khanh Ngoc

IPC分类号： G08B21/04

CPC分类号： G08B21/0423 ,  G08B21/0469 ,  G08B21/0484

摘要： A method and apparatus for recognizing an activity of a monitored individual in an environment are described including receiving a first acoustic signal, performing audio feature extraction on the first acoustic signal in a first temporal window, classifying the first acoustic signal by determining a location of the monitored individual in the environment based on the extracted features of the first acoustic signal in the first temporal window, receiving a second audio signal, performing audio feature extraction of the second acoustic signal in a second temporal window and classifying the second acoustic signal by determining an activity of the monitored individual in the location in the environment based on the extracted features of the second acoustic signal in the second temporal window.

摘要翻译： 描述了用于识别环境中的被监测个体的活动的方法和设备，包括接收第一声学信号，在第一时间窗中对第一声学信号执行音频特征提取，通过确定第一声学信号的位置 基于在第一时间窗口中提取的第一声学信号的特征来监测环境中的个体;接收第二音频信号;在第二时间窗口中执行第二声学信号的音频特征提取;以及通过确定第二声学信号 基于在第二时间窗口中提取的第二声学信号的特征，监测的个体在环境中的位置的活动。

公开(公告)号：EP3023882B1

公开(公告)日：2017-08-30

申请号：EP15195300.7

申请日：2015-11-19

申请人： Thomson Licensing

发明人： DUONG, Quang Khanh Ngoc ,  OZEROV, Alexey ,  LEFEBVRE, Frédéric

IPC分类号： G06F17/14 ,  G06F17/18 ,  G06F17/30 ,  G10L25/54 ,  G10L25/48 ,  G10L25/18

CPC分类号： G10L19/02 ,  G06F17/141 ,  G06F17/30743 ,  G10L19/0212 ,  G10L19/038 ,  G10L25/18 ,  G10L25/48 ,  G10L25/54

公开(公告)号：EP3189521A1

公开(公告)日：2017-07-12

申请号：EP15766406.1

申请日：2015-08-25

申请人： Thomson Licensing

发明人： DUONG, Quang Khanh Ngoc ,  BERTHET, Pierre ,  ZABRE, Eric ,  KERDRANVAT, Michel

IPC分类号： G10L21/0208 ,  G10L21/0272 ,  G10L21/0216

CPC分类号： G10L21/0205 ,  G10L21/0208 ,  G10L21/0272 ,  G10L2021/02166 ,  H04R1/406 ,  H04R3/005

摘要： A recording is usually a mixture of signals from several sound sources. The directions of the dominant sources in the recording may be known or determined using a source localization algorithm. To isolate or focus on a target source, multiple beamformers may be used. In one embodiment, each beamformer points to a direction of a dominant source and the outputs from the beamformers are processed to focus on the target source. Depending on whether the beamformer pointing to the target source has an output that is larger than the outputs of other beamformers, a reference signal or a scaled output of the beamformer pointing to the target source can be used to determine the signal corresponding to the target source. The scaling factor may depend on a ratio of the output of the beamformer pointing to the target source and the maximum value of the outputs of the other beamformers.

摘要翻译： 录音通常是来自多个声源的信号的混合。 记录中主要来源的方向可能是已知的或使用源定位算法确定的。 为了隔离或聚焦目标源，可以使用多个波束形成器。 在一个实施例中，每个波束形成器指向主导源的方向，并且来自波束形成器的输出被处理以聚焦在目标源上。 取决于指向目标源的波束成形器是否具有大于其他波束成形器的输出的输出，可以使用指向目标源的波束成形器的参考信号或缩放输出来确定对应于目标源的信号 。 缩放因子可取决于指向目标源的波束成形器的输出与其他波束成形器的输出的最大值之比。

公开(公告)号：EP3493173A1

公开(公告)日：2019-06-05

申请号：EP17306659.8

申请日：2017-11-30

申请人： THOMSON LICENSING

发明人： DEMARTY, Claire-Hélène ,  DUONG, Quang Khanh Ngoc ,  LEFEBVRE, Frédéric

IPC分类号： G08B21/24

摘要： The disclosure relates to a method including:
- monitoring of events captured by sensors of a communication system, said monitoring being performed during a monitoring time interval taking account of a reference time of day when a first electronic device of the communication system is in a reference location;
- generating an alert according to a similarity between a reference pattern of events and the monitored events, the alert being generated at a time different from the reference time of day.
The disclosure also relates to corresponding electronic device, communication system, computer readable program product and computer readable storage medium.

公开(公告)号：EP3392883A1

公开(公告)日：2018-10-24

申请号：EP18165900.4

申请日：2018-04-05

申请人： THOMSON LICENSING

发明人： PAREKH, Sanjeel ,  OZEROV, Alexey ,  DUONG, Quang Khanh Ngoc ,  RICHARD, Gaël ,  ESSID, Slim ,  PEREZ, Patrick

IPC分类号： G10L21/0272 ,  G10L25/57

CPC分类号： G10L21/028 ,  G10L21/0224 ,  G10L21/0232 ,  G10L21/0272 ,  G10L25/57

摘要： The present disclosure relates to a method for processing an input signal comprising an audio component and to the corresponding electronic device, non-transitory computer readable program product and computer readable storage medium.
According to an embodiment of the present disclosure, the method comprises:
• obtaining a set of time parameters from a time frequency transformation of the audio component of the input signal, said audio component being a mixture of audio signals comprising at least one first audio signal of a first audio source;
• determining at least one motion feature of said first audio source from a visual sequence corresponding to the first audio signal;
• obtaining a weight vector of the set of time parameters based on the motion feature; and
• determining a time frequency transformation of the first audio signal based on the weight vector.

公开(公告)号：EP3151535A1

公开(公告)日：2017-04-05

申请号：EP15306529.7

申请日：2015-09-29

申请人： Thomson Licensing

发明人： HELLIER, Pierre ,  DUONG, Quang Khanh Ngoc ,  ALLIE, Valérie ,  LEYENDECKER, Philippe

IPC分类号： H04N5/232

CPC分类号： H04N5/232 ,  H04N5/23212 ,  H04R1/406 ,  H04R3/005 ,  H04R27/00 ,  H04R29/00 ,  H04R2227/003 ,  H04R2499/11 ,  H04S2400/15

摘要： A plenoptic camera and associated method is provided. The camera has an array of sensors for generating digital images. The images have associated audio signals. The array of sensors are configured to capture digital images associated with a default spatial coordinate and are also configured to receive control input from a processor to change focus from said default spatial coordinate to a new spatial coordinate based on occurrence of an event at said new spatial coordinate.

摘要翻译： 本发明提供一种全光照相机和相关方法。 照相机具有的传感器阵列，用于产生数字图像。 这些图像具有相关联的音频信号。 传感器阵列被配置成捕捉与默认的空间坐标相关联的数字图像，并因此被配置为接收控制输入从处理器到改变焦点从所述默认的空间坐标到一个新的空间基于在所述新的空间的事件的发生坐标 协调。

公开(公告)号：EP2926273A1

公开(公告)日：2015-10-07

申请号：EP13795513.4

申请日：2013-11-26

申请人： Thomson Licensing

发明人： DUONG, Quang Khanh Ngoc ,  THUDOR, Franck

IPC分类号： G06F17/30

CPC分类号： H04N21/4302 ,  G06F17/30787 ,  H04N9/87 ,  H04N21/23439 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/8456

摘要： This method for synchronizing two versions (4,6) of a multimedia content, each version (4,6) comprising a plurality of video frames, comprises steps of: a) extracting (20) audio fingerprints from each version (4,6) of the multimedia content; b) determining (24,26,28) at least two temporal matching periods between both versions (4,6) using the extracted audio fingerprints; c) mapping (30,32,34) the video frames of both versions (4,6) using the determined temporal matching periods.

公开(公告)号：EP3313102A1

公开(公告)日：2018-04-25

申请号：EP16306382.9

申请日：2016-10-21

申请人： Thomson Licensing

发明人： DUONG, Quang Khanh Ngoc ,  ERIKSSON, Brian Charles ,  GILBERTON, Philippe ,  DELAUNAY, Christophe

IPC分类号： H04S7/00 ,  H04R27/00

CPC分类号： H04S7/303 ,  G10L25/84 ,  H03G3/32 ,  H04R27/00 ,  H04R2499/13 ,  H04S7/302 ,  H04S2400/13

摘要： The present principles generally relate to audio apparatus, methods, and computer program products and in particular, to improvements that adjust the sound level or levels of one or more audio outputs of an audio system based on the determined origin and/or direction of propagation of a detected human voice in a location. Such an adjustment may be to decrease, mute, or increase the sound level of an audio output producing sound in the direction of the origin of the voice. A sound level produced by other audio outputs may be unchanged.

摘要翻译： 本原理通常涉及音频设备，方法和计算机程序产品，并且具体地涉及基于所确定的原点和/或传播方向来调整音频系统的一个或多个音频输出的声级或级别的改进 在某个位置检测到的人声。 这样的调整可以是减小，静音或增加音频输出产生的声音在声音起源方向上的声级。 其他音频输出产生的声音电平可能保持不变。

公开(公告)号：EP3293733A1

公开(公告)日：2018-03-14

申请号：EP16306129.4

申请日：2016-09-09

申请人： Thomson Licensing

发明人： PUY, Gilles ,  DUONG, Quang Khanh Ngoc ,  OZEROV, Alexey ,  PEREZ, Patrick

IPC分类号： G10L19/008 ,  G10L19/20

CPC分类号： G10L21/0272 ,  G06K9/6223 ,  G06N3/0454 ,  G10H2210/056 ,  G10H2250/311 ,  G10L15/02 ,  G10L19/008 ,  G10L19/20 ,  G10L25/18

摘要： A method is proposed for encoding at least two signals. The method comprises: mixing the at least two signals in a mixture; computing a map Z representative of locations of the at least two signals in a time-frequency plane; obtaining sampling locations of the map Z; sampling the map Z at the sampling locations, the sampling delivering a first list of values Z Ω ; and transmitting the mixture of the at least two signals and a second list of values based on the first list of values Z Ω .

摘要翻译： 提出了一种用于编码至少两个信号的方法。 该方法包括：将至少两个信号混合成混合物; 计算代表所述至少两个信号在时频平面中的位置的地图Z; 获得地图Z的采样位置; 对采样位置处的地图Z进行采样，采样传送值为ZΩ的第一列表; 以及基于所述第一值列表ZΩ传输所述至少两个信号的混合和第二值列表。

公开(公告)号：EP3143619A1

公开(公告)日：2017-03-22

申请号：EP15722182.1

申请日：2015-05-11

申请人： Thomson Licensing

发明人： DUONG, Quang Khanh Ngoc ,  OZEROV, Alexey ,  ELBADAWY, Dalia

IPC分类号： G10L21/0272

CPC分类号： G06F3/165 ,  G10L21/0272

摘要： A method and a system (20) of audio source separation are described. The method comprises: receiving (10) an audio mixture and at least one text query associated to the audio mixture; retrieving (11) at least one audio sample from an auxiliary audio database; evaluating (12) the retrieved audio samples; and separating (13) the audio mixture into a plurality of audio sources using the audio samples. The corresponding system (20) comprises a receiving (21) and a processor (22) configured to implement the method.

摘要翻译： 描述了音频源分离的方法和系统（20）。 该方法包括：接收（10）与音频混合相关联的音频混合和至少一个文本查询; 从辅助音频数据库检索（11）至少一个音频样本; 评估（12）检索的音频样本; 以及使用所述音频样本将所述音频混合分离（13）成多个音频源。 相应的系统（20）包括被配置为实现该方法的接收（21）和处理器（22）。