利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

28 条记录 (耗时 0.025 秒)

    Robust separation of speech signals in a noisy environment
    1.
    发明授权
    Robust separation of speech signals in a noisy environment 有权
    语音信号在嘈杂环境中的鲁棒分离

    公开(公告)号：US07464029B2

    公开(公告)日：2008-12-09

    申请号：US11187504

    申请日：2005-07-22

    申请人： Erik Visser ,  Jeremy Toman ,  Kwokleung Chan

    发明人： Erik Visser ,  Jeremy Toman ,  Kwokleung Chan

    IPC分类号： G10L19/14 ,  G10L11/06 ,  G10L21/02 ,  G10L15/20

    CPC分类号： G10L25/78 ,  G10L21/0272 ,  G10L2021/02165 ,  H04R2410/07

    摘要： 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.

    摘要翻译： 提供了一种用于改善从噪声声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。 输出级更慢地适应，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。

    Robust separation of speech signals in a noisy environment
    2.
    发明申请
    Robust separation of speech signals in a noisy environment 有权
    语音信号在嘈杂环境中的鲁棒分离

    公开(公告)号：US20070021958A1

    公开(公告)日：2007-01-25

    申请号：US11187504

    申请日：2005-07-22

    申请人： Erik Visser ,  Jeremy Toman ,  Kwokleung Chan

    发明人： Erik Visser ,  Jeremy Toman ,  Kwokleung Chan

    IPC分类号： G10L21/02

    CPC分类号： G10L25/78 ,  G10L21/0272 ,  G10L2021/02165 ,  H04R2410/07

    摘要： 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.

    摘要翻译： 提供了一种用于改善从噪声声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。 输出级更慢地适应，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。

    Systems, methods, and apparatus for signal separation using data driven techniques
    3.
    发明授权
    Systems, methods, and apparatus for signal separation using data driven techniques 有权
    使用数据驱动技术进行信号分离的系统，方法和装置

    公开(公告)号：US08160273B2

    公开(公告)日：2012-04-17

    申请号：US12197924

    申请日：2008-08-25

    申请人： Erik Visser ,  Kwokleung Chan ,  Hyun Jin Park

    发明人： Erik Visser ,  Kwokleung Chan ,  Hyun Jin Park

    IPC分类号： H04B15/00

    CPC分类号： G10L21/0272

    摘要： Methods, apparatus, and systems for source separation include a converged plurality of coefficient values that is based on each of a plurality of M-channel signals. Each of the plurality of M-channel signals is based on signals produced by M transducers in response to at least one information source and at least one interference source. In some examples, the converged plurality of coefficient values is used to filter an M-channel signal to produce an information output signal and an interference output signal.

    摘要翻译： 用于源分离的方法，装置和系统包括基于多个M信道信号中的每一个的会聚的多个系数值。 多个M信道信号中的每一个基于由M个换能器响应于至少一个信息源和至少一个干扰源产生的信号。 在一些示例中，收敛的多个系数值用于滤波M信道信号以产生信息输出信号和干扰输出信号。

    Integrated echo cancellation and noise suppression
    5.
    发明授权
    Integrated echo cancellation and noise suppression 有权
    集成回声消除和噪声抑制

    公开(公告)号：US08811601B2

    公开(公告)日：2014-08-19

    申请号：US13079548

    申请日：2011-04-04

    申请人： Asif I. Mohammad ,  Kwokleung Chan ,  Ian Ernan Liu ,  Erik Visser ,  Dinesh Ramakrishnan

    发明人： Asif I. Mohammad ,  Kwokleung Chan ,  Ian Ernan Liu ,  Erik Visser ,  Dinesh Ramakrishnan

    IPC分类号： H04M9/08 ,  H04B3/23

    CPC分类号： H04B3/234 ,  G10L21/0208 ,  G10L2021/02082 ,  G10L2021/02166 ,  H04M9/082

    摘要： A method for echo cancellation and noise suppression is disclosed. Linear echo cancellation (LEC) is performed for a primary microphone channel on an entire frequency band or in a range of frequencies where echo is audible. LEC is performed on one or more secondary microphone channels only on a lower frequency range over which spatial processing is effective. The microphone channels are spatially processed over the lower frequency range after LEC. Non-linear noise suppression post-processing is performed on the entire frequency band. Echo post-processing is performed on the entire frequency band.

    摘要翻译： 公开了一种用于回波消除和噪声抑制的方法。 线性回波消除（LEC）是在整个频带上的主要麦克风通道或在可听见回声的频率范围内执行的。 只有在空间处理有效的较低频率范围上的一个或多个辅助麦克风通道上执行LEC。 麦克风通道在LEC之后的较低频率范围内进行空间处理。 在整个频带上执行非线性噪声抑制后处理。 在整个频带上执行回波后处理。

    INTEGRATED ECHO CANCELLATION AND NOISE SUPPRESSION
    6.
    发明申请
    INTEGRATED ECHO CANCELLATION AND NOISE SUPPRESSION 有权
    综合ECHO消除和噪声抑制

    公开(公告)号：US20120250882A1

    公开(公告)日：2012-10-04

    申请号：US13079548

    申请日：2011-04-04

    申请人： Asif I. Mohammad ,  Kwokleung Chan ,  Ian Eman Liu ,  Erik Visser ,  Dinesh Ramakrishnan

    发明人： Asif I. Mohammad ,  Kwokleung Chan ,  Ian Eman Liu ,  Erik Visser ,  Dinesh Ramakrishnan

    IPC分类号： H04B15/00

    CPC分类号： H04B3/234 ,  G10L21/0208 ,  G10L2021/02082 ,  G10L2021/02166 ,  H04M9/082

    摘要： A method for echo cancellation and noise suppression is disclosed. Linear echo cancellation (LEC) is performed for a primary microphone channel on an entire frequency band or in a range of frequencies where echo is audible. LEC is performed on one or more secondary microphone channels only on a lower frequency range over which spatial processing is effective. The microphone channels are spatially processed over the lower frequency range after LEC. Non-linear noise suppression post-processing is performed on the entire frequency band. Echo post-processing is performed on the entire frequency band.

    摘要翻译： 公开了一种用于回波消除和噪声抑制的方法。 线性回波消除（LEC）是在整个频带上的主要麦克风通道或在可听见回声的频率范围内执行的。 只有在空间处理有效的较低频率范围上的一个或多个辅助麦克风通道上执行LEC。 麦克风通道在LEC之后的较低频率范围内进行空间处理。 在整个频带上执行非线性噪声抑制后处理。 在整个频带上执行回波后处理。

    SYSTEMS, METHODS, AND APPARATUS FOR SIGNAL SEPARATION
    8.
    发明申请
    SYSTEMS, METHODS, AND APPARATUS FOR SIGNAL SEPARATION 有权
    用于信号分离的系统，方法和装置

    公开(公告)号：US20090022336A1

    公开(公告)日：2009-01-22

    申请号：US12197924

    申请日：2008-08-25

    申请人： Erik Visser ,  Kwokleung Chan ,  Hyun Jin Park

    发明人： Erik Visser ,  Kwokleung Chan ,  Hyun Jin Park

    IPC分类号： H04B15/00

    CPC分类号： G10L21/0272

    摘要： Methods, apparatus, and systems for source separation include a converged plurality of coefficient values that is based on each of a plurality of M-channel signals. Each of the plurality of M-channel signals is based on signals produced by M transducers in response to at least one information source and at least one interference source. In some examples, the converged plurality of coefficient values is used to filter an M-channel signal to produce an information output signal and an interference output signal.

    摘要翻译： 用于源分离的方法，装置和系统包括基于多个M信道信号中的每一个的会聚的多个系数值。 多个M信道信号中的每一个基于由M个换能器响应于至少一个信息源和至少一个干扰源产生的信号。 在一些示例中，收敛的多个系数值用于滤波M信道信号以产生信息输出信号和干扰输出信号。

    System and Method for Spectral Analysis
    9.
    发明申请
    System and Method for Spectral Analysis 审中-公开
    光谱分析系统与方法

    公开(公告)号：US20090001262A1

    公开(公告)日：2009-01-01

    申请号：US11659629

    申请日：2004-10-22

    申请人： Erik Visser ,  Tzyy-Ping Jung ,  Kwokleung Chan

    发明人： Erik Visser ,  Tzyy-Ping Jung ,  Kwokleung Chan

    IPC分类号： H01J49/26

    CPC分类号： H01J49/0036 ,  G06K9/6242

    摘要： The system and method for spectral analysis uses a set of spectral data. The spectral data is arranged according to a second dimension, such as time, temperature, position, or other condition. The arranged spectral data is used in a signal separation process, such as an independent component analysis (ICA), which generates independent signals. The independent signals are then used for identifying or quantifying a target component.

    摘要翻译： 光谱分析的系统和方法使用一组光谱数据。 光谱数据根据诸如时间，温度，位置或其他条件的第二维度来布置。 布置的光谱数据用于信号分离过程，例如独立分量分析（ICA），其产生独立的信号。 然后，独立信号用于识别或量化目标分量。

    Systems, methods, apparatus, and computer program products for enhanced active noise cancellation
    10.
    发明授权
    Systems, methods, apparatus, and computer program products for enhanced active noise cancellation 有权
    用于增强主动噪声消除的系统，方法，设备和计算机程序产品

    公开(公告)号：US09202455B2

    公开(公告)日：2015-12-01

    申请号：US12621107

    申请日：2009-11-18

    申请人： Hyun Jin Park ,  Kwokleung Chan

    发明人： Hyun Jin Park ,  Kwokleung Chan

    IPC分类号： H04B15/00 ,  G10K11/178

    CPC分类号： G10K11/178 ,  G10K11/17837 ,  G10K2210/1081

    摘要： Uses of an enhanced sidetone signal in an active noise cancellation operation are disclosed. In one example, a method of audio signal processing includes producing an anti-noise signal based on information from a first audio signal. A target component of a second audio signal is separated from a noise component of the second audio signal to produce at least one among a separated target component and a separated noise component. Based on at least one among the separated target component and the separated noise component, an audio output signal is produced.

    摘要翻译： 公开了在主动噪声消除操作中使用增强型侧音信号。 在一个示例中，音频信号处理的方法包括基于来自第一音频信号的信息产生抗噪声信号。 第二音频信号的目标分量与第二音频信号的噪声分量分离，以产生分离的目标分量和分离的噪声分量中的至少一个。 基于分离的目标分量和分离的噪声分量中的至少一个，产生音频输出信号。