公开(公告)号：US08666750B2

公开(公告)日：2014-03-04

申请号：US12023485

申请日：2008-01-31

申请人： Markus Buck ,  Lars König ,  Gerhard Uwe Schmidt

发明人： Markus Buck ,  Lars König ,  Gerhard Uwe Schmidt

IPC分类号： G10L17/00 ,  G10L21/00

CPC分类号： G10L15/28 ,  G10L25/78

摘要： A voice control system allows a user to control a device through voice commands. The voice control system includes a speech recognition unit that receives a control signal from a mobile device and a speech signal from a user. The speech recognition unit configures speech recognition settings in response to the control signal to improve speech recognition.

摘要翻译： 语音控制系统允许用户通过语音命令来控制设备。 语音控制系统包括从移动设备接收控制信号和来自用户的语音信号的语音识别单元。 语音识别单元响应于控制信号配置语音识别设置以改善语音识别。

公开(公告)号：US08392184B2

公开(公告)日：2013-03-05

申请号：US12357258

申请日：2009-01-21

申请人： Markus Buck ,  Klaus Scheufele

发明人： Markus Buck ,  Klaus Scheufele

IPC分类号： G10L15/20

CPC分类号： G10L21/0208 ,  G10L2021/02166

摘要： The invention relates to speech signal processing that detects a speech signal from more than one microphone and obtains microphone signals that are processed by a beamformer to obtain a beamformed signal that is post-filtered signal with a filter that employs adaptable filter weights to obtain an enhanced beamformed signal with the post-filter adapting the filter weights with previously learned filter weights.

摘要翻译： 本发明涉及语音信号处理，其检测来自多于一个麦克风的语音信号，并获得由波束形成器处理的麦克风信号，以获得具有滤波后信号的波束形成信号，该滤波器采用适应滤波器权重以获得增强的 波束形成的信号与后置滤波器使用先前学习的滤波器权重来适配滤波器权重。

公开(公告)号：US08374358B2

公开(公告)日：2013-02-12

申请号：US12749066

申请日：2010-03-29

申请人： Markus Buck ,  Tobias Wolff ,  Toby Christian Lawin-Ore ,  Samuel Ngouoko Mboungueng ,  Gerhard Schmidt

发明人： Markus Buck ,  Tobias Wolff ,  Toby Christian Lawin-Ore ,  Samuel Ngouoko Mboungueng ,  Gerhard Schmidt

IPC分类号： H04B15/00 ,  H04R3/00

CPC分类号： G10K11/002 ,  G10L21/0208 ,  G10L2021/02165 ,  G10L2021/02166 ,  H04R3/005 ,  H04R2499/13

摘要： The invention provides a method for determining a noise reference signal for noise compensation and/or noise reduction. A first audio signal on a first signal path and a second audio signal on a second signal path are received. The first audio signal is filtered using a first adaptive filter to obtain a first filtered audio signal. The second audio signal is filtered using a second adaptive filter to obtain a second filtered audio signal. The first and the second filtered audio signal are combined to obtain the noise reference signal. The first and the second adaptive filter are adapted such as to minimize a wanted signal component in the noise reference signal.

摘要翻译： 本发明提供了一种用于确定用于噪声补偿和/或降噪的噪声参考信号的方法。 接收第一信号路径上的第一音频信号和第二信号路径上的第二音频信号。 使用第一自适应滤波器对第一音频信号进行滤波，以获得第一滤波音频信号。 使用第二自适应滤波器对第二音频信号进行滤波，以获得第二滤波音频信号。 第一和第二滤波音频信号被组合以获得噪声参考信号。 第一和第二自适应滤波器适于使噪声参考信号中的有用信号分量最小化。

公开(公告)号：US20130024196A1

公开(公告)日：2013-01-24

申请号：US13187971

申请日：2011-07-21

申请人： William F. Ganong, III ,  David Mark Krowitz ,  Tobias Wolff ,  Markus Buck

发明人： William F. Ganong, III ,  David Mark Krowitz ,  Tobias Wolff ,  Markus Buck

IPC分类号： G10L17/00

CPC分类号： G10L17/00

摘要： Systems, methods, and apparatus for using at least one mobile device to receive a representation of at least one audio signal. In some embodiments, the at least one audio signal comprises speech of at least one of a plurality of first participants of a meeting, the plurality of first participants participating in the meeting from a first location, and the at least one audio signal may be audibly rendered to at least one second participant of the meeting at a second location different from the first location. In some embodiments, the at least one mobile device may further receive an indication of an identity of a leading speaker of the speech in the at least one audio signal, the leading speaker being identified from among the plurality of first participants, and may render the identity of the leading speaker to the at least one second participant.

摘要翻译： 用于使用至少一个移动设备来接收至少一个音频信号的表示的系统，方法和装置。 在一些实施例中，所述至少一个音频信号包括会议的多个第一参与者中的至少一个的语音，所述多个第一参与者从第一位置参与会议，并且所述至少一个音频信号可以是可听见的 在与第一位置不同的第二位置处呈现给会议的至少一个第二参与者。 在一些实施例中，所述至少一个移动设备还可以在所述至少一个音频信号中接收所述语音的主要扬声器的身份的指示，所述主要扬声器从所述多个第一参与者中识别，并且可以使 领先的扬声器的身份到至少一个第二参与者。

公开(公告)号：US08180069B2

公开(公告)日：2012-05-15

申请号：US12189545

申请日：2008-08-11

申请人： Markus Buck ,  Tobias Wolff

发明人： Markus Buck ,  Tobias Wolff

IPC分类号： H04B15/00

CPC分类号： H04R3/005 ,  H04R2430/25

摘要： A signal processor uses input devices to detect speech or aural signals. Through a programmable set of weights and/or time delays (or phasing) the output of the input devices may be processed to yield a combined signal. The noise contributions of some or each of the outputs of the input devices may be estimated by a circuit element or a controller that processes the outputs of the respective input devices to yield power densities. A short-term measure or estimate of the noise contribution of the respective outputs of the input devices may be obtained by processing the power densities of some or each of the outputs of the respective input devices. Based on the short-term measure or estimate, the noise contribution of the combined signal may be estimated to enhance the combined signal when processed further. An enhancement device or post-filter may reduce noise more effectively and yield robust speech based on the estimated noise contribution of the combined signal.

摘要翻译： 信号处理器使用输入设备来检测语音或听觉信号。 通过一组可编程的权重和/或时间延迟（或定相），可以处理输入设备的输出以产生组合信号。 可以由处理各个输入装置的输出以产生功率密度的电路元件或控制器估计输入装置的一些或每个输出的噪声贡献。 可以通过处理各个输入设备的一些或每个输出的功率密度来获得输入设备的各个输出的噪声贡献的短期测量或估计。 基于短期测量或估计，可以估计组合信号的噪声贡献，以在进一步处理时增强组合信号。 增强装置或后置滤波器可以更有效地降低噪声，并且基于组合信号的估计的噪声贡献产生鲁棒的语音。

公开(公告)号：US20100150375A1

公开(公告)日：2010-06-17

申请号：US12636432

申请日：2009-12-11

申请人： Markus Buck ,  Timo Matheja

发明人： Markus Buck ,  Timo Matheja

IPC分类号： H04B15/00

CPC分类号： G10L25/78 ,  G10L2021/02165

摘要： Embodiments of the invention disclose computer-implemented methods, systems, and computer program products for estimating signal coherence. First, a sound generated by a sound source is detected by a first microphone to obtain a first microphone signal and by a second microphone to obtain a second microphone signal. The first microphone signal is filtered by a first adaptive finite impulse response filter to obtain a first filtered signal. The second microphone signal is filtered by a second adaptive finite impulse response filter, to obtain a second filtered signal. The coherence of the first filtered signal and the second filtered signal is determined based upon the filtered signals. The first and the second microphone signals are filtered such that the difference between the acoustic transfer function for the transfer of the sound from the sound source to the first microphone and the transfer of the sound from the sound source to the second microphone is compensated in the first and second filtered signals.

摘要翻译： 本发明的实施例公开了用于估计信号一致性的计算机实现的方法，系统和计算机程序产品。 首先，由第一麦克风检测由声源产生的声音以获得第一麦克风信号，并由第二麦克风检测第二麦克风信号。 第一麦克风信号被第一自适应有限脉冲响应滤波器滤波以获得第一滤波信号。 第二麦克风信号被第二自适应有限脉冲响应滤波器滤波，以获得第二滤波信号。 基于经滤波的信号确定第一滤波信号和第二滤波信号的相干性。 第一麦克风信号和第二麦克风信号被滤波，以便在声音传输到第一麦克风的声音传递功能与声音从声源传输到第二麦克风之间的差异被补偿在 第一和第二滤波信号。

公开(公告)号：US20100054085A1

公开(公告)日：2010-03-04

申请号：US12547681

申请日：2009-08-26

申请人： Tobias Wolff ,  Markus Buck ,  Gerhard Schmidt ,  Olga González Valbuena ,  Günther Wirsching

发明人： Tobias Wolff ,  Markus Buck ,  Gerhard Schmidt ,  Olga González Valbuena ,  Günther Wirsching

IPC分类号： G01S3/80 ,  H04R3/00

CPC分类号： G01S3/8083

摘要： A method of locating a sound source based on sound received at an array of microphones comprises the steps of determining a correlation function of signals provided by microphones of the array and establishing a direction in which the sound source is located based on at least one eigenvector of a matrix having matrix elements which are determined based on the correlation function. The correlation function has first and second frequency components associated with a first and second frequency band, respectively. The first frequency component is determined based on signals from microphones having a first distance, and the second frequency component is determined based on signals from microphones having a second distance different from the first distance.

摘要翻译： 基于在麦克风阵列处接收到的声音来定位声源的方法包括以下步骤：确定由阵列的麦克风提供的信号的相关函数，并基于至少一个本征向量建立声源所在的方向 具有基于相关函数确定的矩阵元素的矩阵。 相关函数分别具有与第一和第二频带相关联的第一和第二频率分量。 基于来自具有第一距离的麦克风的信号确定第一频率分量，并且基于来自具有不同于第一距离的第二距离的麦克风的信号来确定第二频率分量。

公开(公告)号：US20100014690A1

公开(公告)日：2010-01-21

申请号：US12504333

申请日：2009-07-16

申请人： Tobias Wolff ,  Markus Buck ,  Gerhard Schmidt

发明人： Tobias Wolff ,  Markus Buck ,  Gerhard Schmidt

IPC分类号： H04R3/00

CPC分类号： H04R3/005 ,  H04R2430/20 ,  H04R2430/23

摘要： Embodiments of the present invention relate to methods, systems, and computer program products for signal processing. A first plurality of microphone signals is obtained by a first microphone array. A second plurality of microphone signals is obtained by a second microphone array different from the first microphone array. The first plurality of microphone signals is beamformed by a first beamformer comprising beamforming weights to obtain a first beamformed signal. The second plurality of microphone signals is beamformed by a second beamformer comprising the same beamforming weights as the first beamformer to obtain a second beamformed signal. The beamforming weights are adjusted such that the power density of echo components and/or noise components present in the first and second plurality of microphone signals is substantially reduced.

摘要翻译： 本发明的实施例涉及用于信号处理的方法，系统和计算机程序产品。 第一麦克风信号由第一麦克风阵列获得。 通过与第一麦克风阵列不同的第二麦克风阵列获得第二多个麦克风信号。 第一组多个麦克风信号由包括波束成形权重的第一波束形成器波束形成，以获得第一波束形成信号。 第二组麦克风信号由包括与第一波束形成器相同的波束形成权重的第二波束形成器波束形成，以获得第二波束形成信号。 调整波束成形权重使得第一和第二多个麦克风信号中存在的回波分量和/或噪声分量的功率密度显着降低。

公开(公告)号：US20090067642A1

公开(公告)日：2009-03-12

申请号：US12189545

申请日：2008-08-11

申请人： Markus Buck ,  Tobias Wolff

发明人： Markus Buck ,  Tobias Wolff

IPC分类号： H04B15/00

CPC分类号： H04R3/005 ,  H04R2430/25

摘要： A signal processor uses input devices to detect speech or aural signals. Through a programmable set of weights and/or time delays (or phasing) the output of the input devices may be processed to yield a combined signal. The noise contributions of some or each of the outputs of the input devices may be estimated by a circuit element or a controller that processes the outputs of the respective input devices to yield power densities. A short-term measure or estimate of the noise contribution of the respective outputs of the input devices may be obtained by processing the power densities of some or each of the outputs of the respective input devices. Based on the short-term measure or estimate, the noise contribution of the combined signal may be estimated to enhance the combined signal when processed further. An enhancement device or post-filter may reduce noise more effectively and yield robust speech based on the estimated noise contribution of the combined signal.

摘要翻译： 信号处理器使用输入设备来检测语音或听觉信号。 通过一组可编程的权重和/或时间延迟（或定相），可以处理输入设备的输出以产生组合信号。 可以由处理各个输入装置的输出以产生功率密度的电路元件或控制器估计输入装置的一些或每个输出的噪声贡献。 可以通过处理各个输入设备的一些或每个输出的功率密度来获得输入设备的各个输出的噪声贡献的短期测量或估计。 基于短期测量或估计，可以估计组合信号的噪声贡献，以在进一步处理时增强组合信号。 增强装置或后置滤波器可以更有效地降低噪声，并且基于组合信号的估计的噪声贡献产生鲁棒的语音。

公开(公告)号：US09888316B2

公开(公告)日：2018-02-06

申请号：US14778643

申请日：2013-03-21

申请人： NUANCE COMMUNICATIONS, INC. ,  Timo Matheja ,  Markus Buck

发明人： Timo Matheja ,  Markus Buck

IPC分类号： H04R3/00 ,  G06F3/16 ,  H04M1/60 ,  H04M1/03

CPC分类号： H04R3/00 ,  G06F3/165 ,  H04M1/03 ,  H04M1/6008 ,  H04R3/005 ,  H04R2430/03 ,  H04R2430/23 ,  H04R2499/11

摘要： Embodiments disclosed herein may include determining a signal parameter of a first microphone and a second microphone associated with a computing device. Embodiments may include generating a reference parameter based upon at least one of the parameter of the first microphone and the parameter of the second microphone. Embodiments may include adjusting a tolerance of at least one of the first microphone and the second microphone, based upon the reference parameter. Embodiments may include receiving, at the first microphone, a first speech signal, the first speech signal having a first speech signal magnitude and receiving, at the second microphone, a second speech signal, the second speech signal having a second speech signal magnitude. Embodiments may include comparing at least one of the first speech signal magnitude and the second speech signal magnitude with a third speech signal magnitude and detecting an obstructed microphone based upon the comparison.