Echo cancelation using convolutive blind source separation

    公开(公告)号:US10939205B2

    公开(公告)日:2021-03-02

    申请号:US16389699

    申请日:2019-04-19

    Abstract: For canceling acoustic echoing, a processor receives audio signals comprising a speaker output and an ambient input. The processor further calculates separated output signals from mixed signals using a separating transfer function. The processor calculates a criterion function based on the separated output signals. In addition, the processor calculates an acoustic echo transfer function based on maximizing the a criterion function. The processor separates a source signal from the audio signal using the acoustic echo transfer function.

    STATISTICAL MODEL FOR SYSTEMS INCORPORATING HISTORY INFORMATION
    2.
    发明申请
    STATISTICAL MODEL FOR SYSTEMS INCORPORATING HISTORY INFORMATION 有权
    统计历史信息系统统计模型

    公开(公告)号:US20160125305A1

    公开(公告)日:2016-05-05

    申请号:US14532881

    申请日:2014-11-04

    CPC classification number: G06N7/005

    Abstract: For calculating statistical Markov model-like state transition probabilities, a method represents state transition probabilities between a plurality of statistical Markov model-like states and output probabilities associated with a plurality of previous statistical Markov model-like states. The state transition probabilities between the plurality of previous states depend on a sequence of previous states of the plurality of previous states. The output probabilities associated with each of the plurality of states depend on the sequence of previous states.

    Abstract translation: 为了计算统计马尔可夫模型状态转移概率,方法表示多个统计马尔可夫模型状态之间的状态转移概率和与多个先前的统计马尔科夫模型状态相关联的输出概率。 多个先前状态之间的状态转移概率取决于多个先前状态的先前状态的序列。 与多个状态中的每个状态相关联的输出概率取决于先前状态的顺序。

    ECHO CANCELATION USING CONVOLUTIVE BLIND SOURCE SEPARATION

    公开(公告)号:US20190327557A1

    公开(公告)日:2019-10-24

    申请号:US16389699

    申请日:2019-04-19

    Abstract: For canceling acoustic echoing, a processor receives audio signals comprising a speaker output and an ambient input. The processor further calculates separated output signals from mixed signals using a separating transfer function. The processor calculates a criterion function based on the separated output signals. In addition, the processor calculates an acoustic echo transfer function based on maximizing the a criterion function. The processor separates a source signal from the audio signal using the acoustic echo transfer function.

    Statistical model for systems incorporating history information

    公开(公告)号:US09842300B2

    公开(公告)日:2017-12-12

    申请号:US14532881

    申请日:2014-11-04

    CPC classification number: G06N7/005

    Abstract: For calculating statistical Markov model-like state transition probabilities, a method represents state transition probabilities between a plurality of statistical Markov model-like states and output probabilities associated with a plurality of previous statistical Markov model-like states. The state transition probabilities between the plurality of previous states depend on a sequence of previous states of the plurality of previous states. The output probabilities associated with each of the plurality of states depend on the sequence of previous states.

Patent Agency Ranking