公开(公告)号：WO2006028587A2

公开(公告)日：2006-03-16

申请号：PCT/US2005026195

申请日：2005-07-22

Applicant: SOFTMAX INC ,  VISSER ERIK ,  TOMAN JEREMY ,  DAVIS TOM ,  MOMEYER BRIAN

Inventor： VISSER ERIK ,  TOMAN JEREMY ,  DAVIS TOM ,  MOMEYER BRIAN

IPC: G10L21/02

CPC classification number: H04R3/005 ,  G10L21/0208 ,  G10L21/0272 ,  G10L2021/02161 ,  G10L2021/02165 ,  H04R2430/25

Abstract: A headset is constructed to generate an acoustically distinct speech signal in a noisy acoustic environment. The headset positions a pair of spaced-apart microphones near a user's mouth. The microphones each receive the user s speech, and also receive acoustic environmental noise. The microphone signals, which have both a noise and information component, are received into a separation process. The separation process generates a speech signal that has a substantial reduced noise component. The speech signal is then processed for transmission. In one example, the transmission process includes sending the speech signal to a local control module using a Bluetooth radio.

Abstract translation: 耳机被构造成在噪声声学环境中产生声学上不同的语音信号。 耳机将一对间隔开的麦克风放在用户口附近。 麦克风各自接收用户的语音，并且还接收声学环境噪声。 具有噪声和信息分量的麦克风信号被接收到分离过程中。 分离过程产生具有显着降低的噪声分量的语音信号。 然后处理语音信号进行传输。 在一个示例中，传输过程包括使用蓝牙无线电将语音信号发送到本地控制模块。

公开(公告)号：WO2003003905A2

公开(公告)日：2003-01-16

申请号：PCT/US2002/021277

申请日：2002-07-03

Applicant: SOFTMAX, INC. ,  JUNG, Tzyy-Ping ,  DUANN, Jeng-Ren

Inventor： JUNG, Tzyy-Ping ,  DUANN, Jeng-Ren

IPC: A61B

CPC classification number: A61B5/04525 ,  A61B5/04012 ,  A61B5/044 ,  A61B5/0464 ,  A61B5/7203

Abstract: EKG sensors ((150) are placed on a patient (140) to receive electrocardiogram (EKG) recording signals, which are typically combinations of original signals from different sources, such as pacemaker signals, QRS complex signals, and irregular oscillatory signals that suggest an arrhythmia condition. A computing module (120) uses independent component analysis to separate the recorded EKG signals. The separated signals are displayed to help physicians to analyze heart conditions and to identify probably locations of abnormal heart conditions. At least a portion of the separated signals can be further displayed in a chaos phase space portrait to help detect abnormality in heart conditions.

Abstract translation: EKG传感器（（150）放置在患者（140）上以接收心电图（EKG）记录信号，其通常是来自不同源的原始信号的组合，例如起搏器信号，QRS复合信号 （120）使用独立分量分析来分离记录的EKG信号，分离的信号被显示以帮助医生分析心脏状况并识别心脏状况异常的可能位置。 至少一部分分离的信号可以进一步显示在混沌相空间肖像中以帮助检测心脏状况中的异常。

公开(公告)号：WO2007014136A2

公开(公告)日：2007-02-01

申请号：PCT/US2006/028627

申请日：2006-07-21

Applicant: SOFTMAX, INC.

Inventor： VISSER, Erik ,  TOMAN, Jeremy ,  CHAN, Kwokleung

IPC: G10L21/02

CPC classification number: G10L25/78 ,  G10L21/0272 ,  G10L2021/02165 ,  H04R2410/07

Abstract: A method for improving the quality of a speech signal extracted from a noisy acoustic environment is provided. In one approach, a signal separation process is associated with a voice activity detector. The voice activity detector is a two-channel detector, which enables a particularly robust and accurate detection of voice activity. When speech is detected, the voice activity detector generates a control signal. The control signal is used to activate, adjust, or control signal separation processes or post-processing operations to improve the quality of the resulting speech signal. In another approach, a signal separation process is provided as a learning stage and an output stage. The learning stage aggressively adjusts to current acoustic conditions, and passes coefficients to the output stage. The output stage adapts more slowly, and generates a speech- content signal and a noise dominant signal. When the learning stage becomes unstable, only the learning stage is reset, allowing the output stage to continue outputting a high quality speech signal.

Abstract translation: 提供了一种用于改善从噪声声学环境提取的语音信号的质量的方法。 在一种方法中，信号分离过程与语音活动检测器相关联。 语音活动检测器是双通道检测器，能够对语音活动进行特别鲁棒和准确的检测。 当检测到语音时，语音活动检测器产生控制信号。 控制信号用于激活，调整或控制信号分离处理或后处理操作，以提高所得语音信号的质量。 在另一种方法中，提供信号分离过程作为学习阶段和输出阶段。 学习阶段积极地调整到当前的声学条件，并将系数传递到输出级。 输出级适应较慢，并产生语音内容信号和噪声主导信号。 当学习阶段变得不稳定时，只有学习阶段被复位，允许输出级继续输出高质量的语音信号。

公开(公告)号：WO2004053839A1

公开(公告)日：2004-06-24

申请号：PCT/US2003/039593

申请日：2003-12-11

Applicant: SOFTMAX, INC. ,  VISSER, Erik ,  LEE, Te-Won

Inventor： VISSER, Erik ,  LEE, Te-Won

IPC: G10L21/02

CPC classification number: G10L21/0272

Abstract: A system and method for separating a mixture of audio signal into desired audio signals (430) (e.g., speech) and a noise signal (440) is disclosed. Microphones (310, 320) are positioned to receive the mixed audio signals, and an independent component analysis (ICA) processes (212) the sound mixture using stability constraints. The ICA process (508) uses predefined characteristics of the desired speech signal to identify and isolate a target sound signal (430). Filter coefficients are adapted with a learning rule and filter weight update dynamics are stabilized to assist convergence to a stable separated ICA signal result. The separated signals may be peripherally-processed to further reduce noise effects using post-­processing (214) and pre-processing (220, 230) techniques and information. The proposed system is designed and easily adaptable for implementation on DSP units or CPUs in audio communication hardware environments.

Abstract translation: 公开了一种用于将音频信号的混合分离成所需音频信号（430）（例如语音）和噪声信号（440）的系统和方法。 麦克风（310,320）被定位成接收混合音频信号，并且独立分量分析（ICA）使用稳定性约束来处理（212）声音混合。 ICA处理（508）使用所需语音信号的预定特征来识别和隔离目标声音信号（430）。 滤波器系数适应于学习规则，并且滤波器权重更新动态被稳定以辅助收敛到稳定的分离的ICA信号结果。 可以对分离的信号进行外围处理，以进一步减少使用后处理（214）和预处理（220,230）技术和信息的噪声影响。 所提出的系统设计和易于适应于在音频通信硬件环境中的DSP单元或CPU上的实现。

公开(公告)号：WO2007014136A9

公开(公告)日：2008-05-15

申请号：PCT/US2006028627

申请日：2006-07-21

Applicant: SOFTMAX INC

Inventor： VISSER ERIK ,  TOMAN JEREMY ,  CHAN KWOKLEUNG

IPC: G10L21/02

CPC classification number: G10L25/78 ,  G10L21/0272 ,  G10L2021/02165 ,  H04R2410/07

Abstract: A method for improving the quality of a speech signal extracted from a noisy acoustic environment is provided. In one approach, a signal separation process (180) is associated with a voice activity detector (185). The voice activity detector (185) is a two-channel (178,182) detector, which enables a particularly robust and accurate detection of voice activity. When a speech is detected, the voice activity detector generates a control signal (411). The control signal (411) is used to activate, adjust, or control signal separation processes or post -processing operations (195) to improve the quality of the resulting speech signal. In another approach, a signal separation process (180) is provided as a learning stage (752) and an output stage (756). The learning stage (752) aggressively adjus to current acoustic conditions and passes coefficients to the output stage (756). The output stage (756) adapts more slowly and generates a speech-content signal (181,770) and a noise dominant signal (407,773). When the learning stage (752) becomes unstable only the learning stage (752) is reset, allowing the output stage (756) to continue outputting a high quality speech signal.

Abstract translation: 提供了一种用于改善从噪声声学环境提取的语音信号的质量的方法。 在一种方法中，信号分离过程（180）与语音活动检测器（185）相关联。 语音活动检测器（185）是双通道（178,182）检测器，其能够对语音活动进行特别鲁棒且准确的检测。 当检测到语音时，语音活动检测器产生控制信号（411）。 控制信号（411）用于激活，调整或控制信号分离处理或后处理操作（195）以提高所得语音信号的质量。 在另一方法中，提供信号分离处理（180）作为学习阶段（752）和输出阶段（756）。 学习阶段（752）积极地调节当前声学条件并将系数传递到输出级（756）。 输出级（756）更缓慢地适应并产生语音内容信号（181,770）和噪声主导信号（407,773）。 当学习阶段（752）变得不稳定时，只有学习阶段（752）被复位，允许输出级（756）继续输出高质量语音信号。

公开(公告)号：WO2006044699A2

公开(公告)日：2006-04-27

申请号：PCT/US2005/037082

申请日：2005-10-13

Applicant: SOFTMAX, INC. ,  DUANN, Jeng-Ren ,  JUNG, Tzyy-Ping

Inventor： DUANN, Jeng-Ren ,  JUNG, Tzyy-Ping

CPC classification number: A61B5/0452

Abstract: A method and system decomposes a cardiac signal, such as an electrocardiogram (ECG) signal, into components. The components are then usable to assist in the detection of an abnormal heart condition. More particularly, a single lead sensor is used to generate a single lead cardiac signal. The cardiac signal is segmented into a set of cycle segments according to detected heart waveforms. The cycle segments are aligned and used to generate a set of cross-sectional signals. The cross-sectional signals are aligned and presented as inputs to a signal separation process, which separates the cardiac signal into a set of components. The components may be grouped according to predefined criteria. The components or groups may be analyzed or displayed to assist in the detection of an abnormal cardiac signal, which may be indicative of an abnormal heart condition. In one example, the signal separation process is a non-orthogonal transformation method such as independent component analysis (ICA).

Abstract translation: 方法和系统将诸如心电图（ECG）信号的心脏信号分解成组件。 然后，这些组件可用于辅助检测异常心脏病。 更具体地，使用单引线传感器来产生单引线心脏信号。 根据检测到的心脏波形，心脏信号被分割成一组循环段。 循环段对齐并用于产生一组横截面信号。 横截面信号被对准并呈现为信号分离过程的输入，信号分离过程将心脏信号分离成一组组件。 可以根据预定义的标准对组件进行分组。 可以分析或显示组件或组以帮助检测异常心脏信号，其可以指示异常的心脏状况。 在一个示例中，信号分离过程是诸如独立分量分析（ICA）之类的非正交变换方法。

公开(公告)号：WO2007103037A3

公开(公告)日：2009-04-30

申请号：PCT/US2007004966

申请日：2007-02-27

Applicant: SOFTMAX INC ,  CHAN KWOKLEUNG ,  VISSER ERIK

Inventor： CHAN KWOKLEUNG ,  VISSER ERIK

IPC: G06F15/00

CPC classification number: G10L21/0272 ,  H04L25/03159

Abstract: The present invention relates to blind source separation. More specifically it relates to the blind source separation using frequency domain processes.

Abstract translation: 本发明涉及盲源分离。 更具体地说，它涉及使用频域过程的盲源分离。

公开(公告)号：WO2006044699A3

公开(公告)日：2006-08-17

申请号：PCT/US2005037082

申请日：2005-10-13

Applicant: SOFTMAX INC ,  DUANN JENG-REN ,  JUNG TZYY-PING

Inventor： DUANN JENG-REN ,  JUNG TZYY-PING

IPC: A61B5/02

CPC classification number: A61B5/0452

Abstract: A method and system decomposes a cardiac signal, such as an electrocardiogram (ECG) signal, into components. The components are then usable to assist in the detection of an abnormal heart condition. More particularly, a single lead sensor is used to generate a single lead cardiac signal. The cardiac signal is segmented into a set of cycle segments according to detected heart waveforms. The cycle segments are aligned and used to generate a set of cross-sectional signals. The cross-sectional signals are aligned and presented as inputs to a signal separation process, which separates the cardiac signal into a set of components. The components may be grouped according to predefined criteria. The components or groups may be analyzed or displayed to assist in the detection of an abnormal cardiac signal, which may be indicative of an abnormal heart condition. In one example, the signal separation process is a non-orthogonal transformation method such as independent component analysis (ICA).

Abstract translation: 一种方法和系统将诸如心电图（ECG）信号的心脏信号分解成分量。 这些组件随后可用于帮助检测异常心脏状况。 更具体地说，使用单个导联传感器来生成单个导联心脏信号。 心脏信号根据检测到的心脏波形被分割成一组周期段。 循环段对齐并用于生成一组横截面信号。 横截面信号被对齐并作为信号分离过程的输入呈现，其将心脏信号分离成一组分量。 这些组件可以根据预定义的标准进行分组。 可以分析或显示组件或组以帮助检测异常心脏信号，这可以指示心脏异常状况。 在一个示例中，信号分离过程是诸如独立分量分析（ICA）之类的非正交变换方法。

公开(公告)号：WO2006012578A3

公开(公告)日：2006-08-17

申请号：PCT/US2005026196

申请日：2005-07-22

Applicant: SOFTMAX INC ,  VISSER ERIK ,  LEE TE-WON

Inventor： VISSER ERIK ,  LEE TE-WON

IPC: G10L21/02

CPC classification number: H04R3/005 ,  G10L21/0208 ,  G10L21/0272 ,  G10L2021/02161 ,  G10L2021/02165 ,  H04R2430/25

Abstract: The present invention provides a process (26) for separating a good quality information signal from a noisy acoustic environment (12). The separation process uses a set of a least two spaced-apart transducers (19, 20) to capture noise (13, 15) and information components (14). The transducer signals, which have both a noise and information component, are received into a separation process. The separation process generates one channel that is substantially only noise, and another channel that is a combination of noise and information. An identification process (30) is used to identify which channel has the information component. The noise signal is then used to set process characteristics that are applied to the combination signal to efficiently reduce or eliminate the noise component. In this way, the noise is effectively removed from the combination signal to generate a good qualify information signal. The information signal may be, for example, a speech signal, a seismic signal, a sonar signal, or other acoustic signal.

Abstract translation: 本发明提供一种用于从良好的声音环境（12）分离出良好质量信息信号的方法（26）。 分离过程使用一组至少两个间隔开的换能器（19,20）来捕获噪声（13,15）和信息分量（14）。 具有噪声和信息分量的换能器信号被接收到分离过程中。 分离过程产生基本上只有噪声的一个信道，以及作为噪声和信息的组合的另一个信道。 识别过程（30）用于识别哪个信道具有信息分量。 然后使用噪声信号来设置施加到组合信号的处理特性，以有效地减少或消除噪声分量。 以这种方式，有效地从组合信号中去除噪声以产生良好的限定信息信号。 信息信号可以是例如语音信号，地震信号，声纳信号或其他声信号。

公开(公告)号：WO2007014136A3

公开(公告)日：2007-11-01

申请号：PCT/US2006028627

申请日：2006-07-21

Applicant: SOFTMAX INC

Inventor： VISSER ERIK ,  TOMAN JEREMY ,  CHAN KWOKLEUNG

IPC: G10L21/02

CPC classification number: G10L25/78 ,  G10L21/0272 ,  G10L2021/02165 ,  H04R2410/07

Abstract: A method for improving the quality of a speech signal extracted from a noisy acoustic environment is provided. In one approach, a signal separation process (180) is associated with a voice activity detector (185). The voice activity detector (185) is a two-channel (178,182) detector, which enables a particularly robust and accurate detection of voice activity. When a speech is detected, the voice activity detector generates a control signal (411). The control signal (411) is used to activate, adjust, or control signal separation processes or post -processing operations (195) to improve the quality of the resulting speech signal. In another approach, a signal separation process (180) is provided as a learning stage (752) and an output stage (756). The learning stage (752) aggressively adjus to current acoustic conditions and passes coefficients to the output stage (756). The output stage (756) adapts more slowly and generates a speech-content signal (181,770) and a noise dominant signal (407,773). When the learning stage (752) becomes unstable only the learning stage (752) is reset, allowing the output stage (756) to continue outputting a high quality speech signal.

Abstract translation: 提供了一种用于改善从噪声声学环境提取的语音信号的质量的方法。 在一种方法中，信号分离过程（180）与语音活动检测器（185）相关联。 语音活动检测器（185）是双通道（178,182）检测器，其能够对语音活动进行特别鲁棒且准确的检测。 当检测到语音时，语音活动检测器产生控制信号（411）。 控制信号（411）用于激活，调整或控制信号分离处理或后处理操作（195）以提高所得语音信号的质量。 在另一方法中，提供信号分离处理（180）作为学习阶段（752）和输出阶段（756）。 学习阶段（752）积极地调节当前声学条件并将系数传递到输出级（756）。 输出级（756）更缓慢地适应并产生语音内容信号（181,770）和噪声主导信号（407,773）。 当学习阶段（752）变得不稳定时，只有学习阶段（752）被复位，允许输出级（756）继续输出高质量语音信号。