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

WO2019046170A1 LOCAL AND CLOUD SPEECH RECOGNITION 审中-公开
公开(公告)号：WO2019046170A1
公开(公告)日：2019-03-07
申请号：PCT/US2018/048101
申请日：2018-08-27
申请人： ROKU, INC.
发明人： WOOD, Anthony John , STERN, David , GARNER, Gregory Mack
IPC分类号： G10L15/02 , G10L15/26 , G10L21/02 , G10L15/18 , G10L15/28
CPC分类号： G10L15/30 , G06F3/167 , G10L15/20 , G10L15/22 , G10L21/0208 , G10L2015/223 , G10L2021/02082 , G10L2021/02166 , H04L67/10 , H04R1/326 , H04R3/005 , H04R27/00 , H04R2227/003 , H04R2227/005 , H04R2430/20
摘要： Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for distributing the performance of speech recognition among a remote control device and a voice platform in the cloud. In some embodiments, the remote control device operates to receive a voice input from a user. The remote control device detects a trigger word in the voice input. The remote control device then processes the voice input. The remote control device then transmits the voice input to a voice platform based on the detecting in order to determine an intent associated with the voice input.

2. 发明申请

WO2017198904A1 A METHOD, APPARATUS, SYSTEM AND COMPUTER PROGRAM FOR CONTROLLING A POSITIONING MODULE AND/OR AN AUDIO CAPTURE MODULE 审中-公开
标题翻译：用于控制定位模块和/或音频捕获模块的方法，装置，系统和计算机程序
公开(公告)号：WO2017198904A1
公开(公告)日：2017-11-23
申请号：PCT/FI2017/050373
申请日：2017-05-16
申请人： NOKIA TECHNOLOGIES OY
发明人： LEPPÄNEN, Jussi , LEHTINIEMI, Arto , ERONEN, Antti , CRICRI, Francesco
IPC分类号： G01S5/02 , H04N5/00
CPC分类号： G01S5/021 , G01S5/0205 , G01S19/34 , G06F16/60 , H04R1/326
摘要： Certain examples of the present invention relate to a method, apparatus, system and computer program for controlling a positioning module and/or an audio capture module. Certain examples provide a method (100) comprising: associating (101) one or more positioning modules (501) with one or more audio capture modules (502); and controlling (102) one or more operations of the one or more positioning modules (501) and/or the associated one or more audio capture modules (502) in dependence upon: one or more pre-determined times (202(a)), and one or more pre-determined positions (202(b)).
摘要翻译：本发明的某些示例涉及用于控制定位模块和/或音频捕获模块的方法，装置，系统和计算机程序。某些示例提供了一种方法（100），包括：将一个或多个定位模块（501）与一个或多个音频捕获模块（502）相关联（101）; 以及根据以下各项来控制（102）所述一个或多个定位模块（501）和/或相关联的一个或多个音频捕获模块（502）的一个或多个操作：一个或多个预定时间（202（a）），以及一个或多个预定位置（202（b））。

3. 发明申请

WO2017172054A1 MULTI-CAMERA DATASET ASSEMBLY AND MANAGEMENT WITH HIGH PRECISION TIMESTAMP REQUIREMENTS 审中-公开
标题翻译：高精度时间戳需求的多相机数据集组装和管理
公开(公告)号：WO2017172054A1
公开(公告)日：2017-10-05
申请号：PCT/US2017/017029
申请日：2017-02-08
申请人： INTEL CORPORATION , KANTHAPANIT, Chanitnan (Lu) , NEWPOL, Richard , HOOK, Joseph A. , NARAYANSWAMY, Ramkumar , SUN, Sheldon L. , TAGGART, Kevin M. , SAUVAGEAU, Christopher T. , PITLA, Rao S. , MOSLEH, Yassir
发明人： KANTHAPANIT, Chanitnan (Lu) , NEWPOL, Richard , HOOK, Joseph A. , NARAYANSWAMY, Ramkumar , SUN, Sheldon L. , TAGGART, Kevin M. , SAUVAGEAU, Christopher T. , PITLA, Rao S. , MOSLEH, Yassir
IPC分类号： H04N21/8547 , H04N21/236 , H04N21/434 , H04N21/218
CPC分类号： H04N21/8547 , H04N5/05 , H04N5/0675 , H04N5/247 , H04N21/234 , H04N21/242 , H04R1/326 , H04R1/406 , H04R3/005 , H04R2499/11
摘要： A method and apparatus for synchronizing data captured by multiple image and non-image data capture devices using timing information. In one embodiment, the device comprises a plurality of interfaces operable to receive streaming data from each of a plurality of image and non-image capture devices and timestamping logic implemented, at least in part, in hardware and coupled to the plurality of interfaces to generate and assign timestamp information to each set of data captured by individual capture devices of the plurality of image and non-image capture devices to indicate when the data was captured, where the timestamp information is synchronized to a single timestamp reference clock. The device also comprises processing logic coupled to the timestamping logic to group image data from image capture devices with data from non-image capture devices using the timestamp information.
摘要翻译：用于使用定时信息来同步由多个图像和非图像数据捕获设备捕获的数据的方法和设备。在一个实施例中，该设备包括可操作以从多个图像捕获设备和非图像捕获设备中的每一个接收流数据的多个接口以及至少部分地以硬件实现并且耦合到多个接口以生成时间戳逻辑以生成并且将时间戳信息分配给由多个图像捕获设备和非图像捕获设备中的各个捕获设备捕获的每组数据，以指示数据何时被捕获，其中时间戳信息被同步到单个时间戳参考时钟。该设备还包括耦合到时间戳逻辑的处理逻辑，用于使用时间戳信息将来自图像捕获设备的图像数据与来自非图像捕获设备的数据分组在一起。

4. 发明申请

WO2016175929A1 OFFSET CARTRIDGE MICROPHONES 审中-公开
公开(公告)号：WO2016175929A1
公开(公告)日：2016-11-03
申请号：PCT/US2016/022773
申请日：2016-03-17
申请人： SHURE ACQUISITION HOLDINGS, INC.
发明人： SHUMARD, Brent, Robert , CANFIELD, Gregory, H. , GILBERT, Mark
IPC分类号： H04R3/00 , H04R19/01 , H04R27/00
CPC分类号： H04R1/326 , H04R1/08 , H04R3/00 , H04R3/005 , H04R3/04 , H04R19/016 , H04R19/04 , H04R27/00 , H04R2410/03 , H04R2430/20
摘要： Offset cartridge microphones are provided that include multiple unidirectional microphone cartridges mounted in an offset geometry. Various desired polar patterns and/or desired steering angles can be formed by processing the audio signals from the multiple cartridges, including a toroidal polar pattern. The offset geometry of the cartridges may include mounting the cartridges so that they are immediately adjacent to one another and so that their center axes are offset from one another. The microphones may have a more consistent on-axis frequency response and may more uniformly form desired polar patterns and/or desired steering angles by reducing the interference and reflections within and between the cartridges.
摘要翻译：提供了偏移式麦克风麦克风，包括以偏移几何形式安装的多个单向麦克风墨盒。可以通过处理来自多个盒的音频信号（包括环形极性图案）来形成各种期望的极性图案和/或期望的转向角。盒的偏移几何形状可以包括安装盒，使得它们彼此紧邻并且使得它们的中心轴彼此偏移。麦克风可以具有更一致的轴上频率响应，并且可以通过减小墨盒内和之间的干涉和反射来更均匀地形成期望的极性图案和/或期望的转向角。

5. 发明申请

WO2016138046A1 SOUND SOURCE LOCALIZATION USING SENSOR FUSION 审中-公开
标题翻译：使用传感器融合的声源定位
公开(公告)号：WO2016138046A1
公开(公告)日：2016-09-01
申请号：PCT/US2016/019204
申请日：2016-02-23
申请人： INVENSENSE, INC.
发明人： OLIAEI, Omid
IPC分类号： G01S5/18 , G10L21/0216
CPC分类号： H04R1/406 , G01S3/802 , G10L2021/02166 , H04R1/326 , H04R3/005 , H04R19/005 , H04R19/04 , H04R2201/40
摘要： Sound source localization using sensor fusion is presented herein. A device can include a sensor component that is configured to receive, from microphone(s), acoustic information corresponding to a sound source, and receive, from a set of sensors, motion information corresponding to the device. Further, the device can include a sensor fusion component that is configured to determine, based on the acoustic information and the motion information, coordinate information representing a location of the device with respect to the sound source, and send the coordinate information directed to a computing device. In an example, the sensor fusion component can determine an orientation of the device based on the motion information, and determine the coordinate information based on the orientation. In another example, the sensor fusion component can determine an angle of arrival of an acoustic wave from the sound source, and determine the coordinate information based on the angle of arrival.
摘要翻译：本文介绍使用传感器融合的声源定位。设备可以包括被配置为从麦克风接收对应于声源的声学信息并且从一组传感器接收与该设备相对应的运动信息的传感器部件。此外，该装置可以包括传感器融合组件，其被配置为基于声学信息和运动信息来确定表示设备相对于声源的位置的坐标信息，并且发送指向计算的坐标信息设备。在一个示例中，传感器融合部件可以基于运动信息确定设备的方向，并且基于取向来确定坐标信息。在另一示例中，传感器融合部件可以确定来自声源的声波的到达角度，并且基于到达角度来确定坐标信息。

6. 发明申请

WO2016126039A1 소리 수집 단말, 소리 제공 단말, 소리 데이터 처리 서버 및 이들을 이용한 소리 데이터 처리 시스템 审中-公开
标题翻译：声音收集终端，声音提供终端，声音数据处理服务器和声音数据处理系统
公开(公告)号：WO2016126039A1
公开(公告)日：2016-08-11
申请号：PCT/KR2016/000840
申请日：2016-01-27
申请人： 서울대학교 산학협력단
发明人： 김수환 , 김세윤 , 김민재
IPC分类号： H04R3/00 , H04R1/40
CPC分类号： H04R1/40 , H04R1/08 , H04R1/326 , H04R3/005 , H04R2430/20
摘要： 본 실시예에 따른 소리 데이터 처리 시스템은, 복수의 소리 수집 단말들, 복수의 소리 제공 단말들과 서버를 포함하는 시스템으로, 복수의 소리 수집 단말과 소리 제공 단말들 중 각각의 소리 수집 단말과 소리 제공 단말은 위치와 지향 방향을 가지고 소리를 수집하는 소리 수집 수단과 위치와 지향 방향을 가지고 소리를 제공하는 소리 제공 수단, 소리 수집 수단과 소리 제공 수단의 위치를 검출하는 위치 검출 수단과, 지향 방향을 검출하는 방향 검출 수단 및 위치 검출 수단이 검출한 위치에 대응하는 위치 데이터와 방향 검출 수단이 검출한 지향 방향에 대응하는 지향 방향 데이터를 포함하는 보충 데이터(supplementary data) 및 소리 수집 수단이 수집한 소리에 대응하는 소리 데이터(sound data)를 네트워크를 통하여 전송하는 통신 모듈을 포함한다.
摘要翻译：根据本实施例的声音数据处理系统是包括多个声音收集终端，多个声音提供终端和服务器，每个收音终端和声音提供终端，从多个声音收集终端和声音提供终端，包括：收集装置，用于收集具有位置和方位方向的声音; 用于提供具有位置和取向方向的声音的声音提供装置; 位置检测装置，用于检测声音收集装置和声音提供装置的位置; 方向检测装置，用于检测取向方向; 补充数据，包括对应于由位置检测装置检测到的位置的位置数据，以及与由方向检测装置检测到的定向方向相对应的定位方向数据; 以及通过网络发送对应于由声音采集装置收集的声音的声音数据的通信模块。

7. 发明申请

WO2016061076A1 USER EXPERIENCE ORIENTED AUDIO SIGNAL PROCESSING 审中-公开
标题翻译：用户体验方向的音频信号处理
公开(公告)号：WO2016061076A1
公开(公告)日：2016-04-21
申请号：PCT/US2015/055291
申请日：2015-10-13
申请人： DOLBY LABORATORIES LICENSING CORPORATION
发明人： MA, Guilin , ZHENG, Xiguang , ZHANG, Chen , SUN, Xuejing
IPC分类号： H04S7/00 , H04M1/60 , H04R3/00 , H04R1/32
CPC分类号： H04R3/04 , G10L21/0232 , G10L2021/02166 , H04M1/6016 , H04M1/605 , H04R1/326 , H04R1/406 , H04R3/005 , H04R29/001 , H04R29/004 , H04R29/005 , H04R2201/40 , H04R2201/401 , H04R2201/403 , H04R2430/20 , H04R2499/11 , H04S7/302
摘要： Example embodiments disclosed herein relate to user experience oriented audio signal processing. There is provided a method for user experience oriented audio signal processing. The method includes obtaining a first audio signal from an audio sensor of an electronic device; computing, based on the first audio signal, a compensation factor for an acoustic path from the electronic device to a listener and applying the compensation factor to a second audio signal outputted from the electronic device. Corresponding system and computer program products are disclosed.
摘要翻译：本文公开的示例实施例涉及面向用户体验的音频信号处理。提供了一种用于面向用户体验音频信号处理的方法。该方法包括从电子设备的音频传感器获得第一音频信号; 基于所述第一音频信号，计算从所述电子设备到收听者的声学路径的补偿因子，并将所述补偿因子应用于从所述电子设备输出的第二音频信号。公开了相应的系统和计算机程序产品。

8. 发明申请

WO2015013058A1 ADAPTIVE BEAMFORMING FOR EIGENBEAMFORMING MICROPHONE ARRAYS 审中-公开
标题翻译：用于微波炉阵列的自适应波束形成
公开(公告)号：WO2015013058A1
公开(公告)日：2015-01-29
申请号：PCT/US2014/046607
申请日：2014-07-15
申请人： MH ACOUSTICS, LLC
发明人： ELKO, Gary, W. , MEYER, Jens, M.
IPC分类号： H04R3/00
CPC分类号： H04R1/326 , H04R3/005 , H04R3/04 , H04R2201/401 , H04R2430/23 , H04S2400/15
摘要： An exemplary audio signal processing system includes a modal decomposer and an adaptive modal beamformer. The modal decomposer generates a plurality of zeroth-order eigenbeams from audio signals from an (e.g., spherical) array of audio sensors. The adaptive modal beamformer (i) steers the zeroth-order eigenbeams to a specified direction, (ii) adaptively generates a plurality of weighting coefficients for the plurality of zeroth-order eigenbeams, where the plurality of weighting coefficients satisfy a constraint of having only non-negative values, (iii) respectively applies the plurality of adaptively generated weighting coefficients to the plurality of steered, zeroth-order eigenbeams to generate a plurality of weighted, steered, zeroth-order eigenbeams, and (iv) combines the plurality of weighted, steered, zeroth-order eigenbeams to generate an output audio signal. Some embodiments have a further constraint that the weighting coefficients sum to a specified value (e.g., one).
摘要翻译：示例性音频信号处理系统包括模态分解器和自适应模态波束形成器。模态分解器从音频传感器（例如，球面）阵列的音频信号产生多个零级本征束。自适应模态波束形成器（i）将第零阶本征波束引导到指定方向，（ii）自适应地生成多个零阶本征波束的多个加权系数，其中多个加权系数满足只有非零阶本征波束的约束，（iii）分别将多个自适应生成的加权系数分别应用于多个转向零阶本征束，以生成多个加权的，转向的零级本征束，并且（iv）将多个加权的，转向，零阶本征波束以产生输出音频信号。一些实施例具有进一步的约束，即加权系数与指定值（例如，一个）相加。

9. 发明申请

WO2014108492A1 MICROPHONE ARRANGEMENT WITH IMPROVED DIRECTIONAL CHARACTERISTIC 审中-公开
标题翻译：具有改进的方向特性的麦克风配置
公开(公告)号：WO2014108492A1
公开(公告)日：2014-07-17
申请号：PCT/EP2014/050360
申请日：2014-01-10
申请人： INSTITUT FÜR RUNDFUNKTECHNIK GMBH
发明人： GROH, Jens
IPC分类号： H04R1/40 , H04R3/00
CPC分类号： H04R1/326 , H04R1/406 , H04R3/005
摘要： A microphone arrangement with improved directional characteristics is proposed. The microphone arrangement is provided with at least two microphones (100, 102) and a signal processing arrangement (105). The signal processing arrangement is provided with a first (108) and a second input (109) for receiving the microphone signals of the at least two microphones. The inputs (108,109) are coupled to signal inputs of a first (110) and a second (111) multiplication circuit. The multiplication circuits are provided with control inputs for receiving respective first and second control signals, and with signal outputs. A control signal generator (112) is provided for generating the first and second control signals for the multiplication circuits (110,111). An arrangement (114) for a power corrected summation is provided, having a first and a second input coupled to the outputs of the first and second multiplication circuit, respectively, and having an output. A signal combination circuit (116) is provided with a first input (117) coupled to the output of the power corrected summation arrangement (114), a second input (118) coupled to one of the at least two microphones (102), and an output (119) coupled to the output (120) of the combination circuit (116).The first multiplication circuit (110) is adapted to multiply the signal applied to its input by a multiplication factor A*(l-g) 1/2, under the influence of the first control signal. The second multiplication circuit (111) is adapted to multiply the signal applied to its input by a multiplication factor B*g 1/2 under the influence of the second control signal. The multiplication factor g is frequency dependent (g[f]), and A and B are constant values, whose absolute values are preferably equal to 1. Further, A = B or A = -B applies. (Fig. l) Preferably, the multiplication factor g[f], below a first frequency value, has a smaller value for increasing frequencies. Below a second frequency value that is smaller than the first frequency value, g[f] is a constant value (V), preferably equal to zero. (Fig. 2a) Thereby, a microphone arrangement can be obtained which exhibits a desired directional characteristics over an increased frequency range.
摘要翻译：提出了具有改进的方向特性的麦克风装置。麦克风装置设置有至少两个麦克风（100,102）和信号处理装置（105）。信号处理装置具有用于接收至少两个麦克风的麦克风信号的第一输入（108）和第二输入（109）。输入（108,109）耦合到第一（110）和第二（111）乘法电路的信号输入。乘法电路设置有用于接收相应的第一和第二控制信号以及信号输出的控制输入。提供控制信号发生器（112），用于产生乘法电路（110,111）的第一和第二控制信号。提供了用于功率校正求和的装置（114），其具有分别耦合到第一和第二乘法电路的输出并具有输出的第一和第二输入。信号组合电路（116）设置有耦合到功率校正求和装置（114）的输出端的第一输入端（117），耦合到至少两个麦克风（102）之一的第二输入端（118），以及耦合到组合电路（116）的输出（120）的输出（119）。第一乘法电路（110）适于将施加到其输入的信号乘以乘法因子A *（lg）1/2，在第一控制信号的影响下。第二乘法电路（111）适于在第二控制信号的影响下将施加到其输入的信号乘以乘法因子B * g1 / 2。乘法因子g是频率相关的（g [f]），A和B是常数值，其绝对值优选等于1.此外，A = B或A = -B。（图1）优选地，低于第一频率值的乘法因子g [f]对于增加频率具有较小的值。低于第一频率值的第二频率值，g [f]是常数值（V），优选等于零。（图2a）因此，可以获得在增加的频率范围内表现出期望的方向特性的麦克风装置。

10. 发明申请

WO2014093653A1 SPATIAL INTERFERENCE SUPPRESSION USING DUAL- MICROPHONE ARRAYS 审中-公开
标题翻译：使用双麦克风阵列的空间干扰抑制
公开(公告)号：WO2014093653A1
公开(公告)日：2014-06-19
申请号：PCT/US2013/074727
申请日：2013-12-12
申请人： CISCO TECHNOLOGY, INC.
发明人： SUN, Haohai , MOBERG, Espen
IPC分类号： H04R3/00 , H04R1/40 , G10L21/0216
CPC分类号： H04R3/005 , H04R1/326 , H04R1/406 , H04R2430/25
摘要： Systems, processes, devices, apparatuses, algorithms and computer readable medium for suppressing spatial interference using a dual microphone array for receiving, from a first microphone and a second microphone that are separated by a predefined distance, and that are configured to receive source signals, respective first and second microphone signals based on received source signals. A phase difference between the first and the second microphone signals is calculated based on the predefined distance. An angular distance between directions of arrival of the source signals and a desired capture direction is calculated based on the phase difference. Directional-filter coefficients are calculated based on the angular distance. Undesired source signals are filtered from an output based on the directional-filter coefficients.
摘要翻译：用于使用双麦克风阵列抑制空间干扰的系统，过程，设备，装置，算法和计算机可读介质，用于从分离预定距离的第一麦克风和第二麦克风接收并配置为接收源信号，基于所接收的源信号的相应的第一和第二麦克风信号。基于预定距离计算第一和第二麦克风信号之间的相位差。基于相位差计算源信号到达方向与期望捕获方向之间的角距离。基于角距离计算方向滤波器系数。基于方向滤波器系数，从输出滤波不期望的源信号。

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