SYSTEMS AND METHODS FOR PARALLELIZING AND PIPELINING A TUNABLE BLIND SOURCE SEPARATION FILTER
    11.
    发明公开
    SYSTEMS AND METHODS FOR PARALLELIZING AND PIPELINING A TUNABLE BLIND SOURCE SEPARATION FILTER 有权
    用于平行化和流水化可调式盲源分离过滤器的系统和方法

    公开(公告)号:EP3293882A1

    公开(公告)日:2018-03-14

    申请号:EP17174816.3

    申请日:2017-06-07

    IPC分类号: H03H21/00 H04B1/10 G01S7/285

    摘要: A method 1200 of processing a plurality of time-varying signals 114/116 received at a sensor 103 communicatively coupled to a signal data processor 101 to identify at least one parameter of at least one of the plurality of time-varying signals 114/116 is provided. The method 1200 includes receiving 1202, at a plurality of blind source separation (BSS) modules 120 of the signal data processor 101, signals derived from the plurality of time-varying signals 114/116, each BSS module 120 of the plurality of BSS modules 120 including a filtering subsystem 207 having a pipelined architecture and a parallelized architecture. The method 1200 also includes generating a plurality of blind source separated signals 129, and transmitting at least one pulse descriptor word (PDW) parameter vector signal 138 to a computing device 132 of the signal data processor 101. The method 1200 further includes identifying the at least one parameter from the at least one PDW parameter vector signal 138, and outputting the at least one parameter from the signal data processor 101.

    摘要翻译: 处理在通信地耦合到信号数据处理器101的传感器103接收的多个时变信号114/116以识别多个时变信号114/116中的至少一个的至少一个参数的方法1200是 提供。 方法1200包括在信号数据处理器101的多个盲源分离(BSS)模块120处接收从多个时变信号114/116导出的信号,多个BSS模块中的每个BSS模块120 120包括具有流水线架构和并行架构的过滤子系统207。 方法1200还包括生成多个盲源分离信号129,并且将至少一个脉冲描述符字(PDW)参数矢量信号138发送到信号数据处理器101的计算设备132.方法1200还包括识别at 来自至少一个PDW参数矢量信号138的至少一个参数,并且从信号数据处理器101输出至少一个参数。

    SOUND SOURCE SEPARATION APPARATUS
    12.
    发明公开
    SOUND SOURCE SEPARATION APPARATUS 审中-公开
    声源分离装置

    公开(公告)号:EP3279896A1

    公开(公告)日:2018-02-07

    申请号:EP17184363.4

    申请日:2017-08-01

    摘要: A sound source separation apparatus includes: a separation-matrix processor that transforms a plurality of observation signals corresponding to sounds being propagated from a plurality of sound sources into a frequency-domain signal group the separation-matrix processor updating a separation matrix based on the frequency-domain signal group and transforming the updated separation matrix into time-series filter coefficients to output; a filter-coefficient transformer that partially removes non-causal components from the filter coefficients to transform the filter coefficients, and a separator that supplies the filter coefficients to a filter group, the separator generating a plurality of separation signals separated from the plurality of observation signals corresponding to the separation matrix.

    摘要翻译: 声源分离设备包括:分离矩阵处理器,用于将与从多个声源传播的声音相对应的多个观测信号变换为频域信号组,分离矩阵处理器基于频率更新分离矩阵 并将更新后的分离矩阵变换为时间序列滤波器系数输出; 滤波器系数变换器,部分地从滤波器系数中去除非因果分量以变换滤波器系数;以及分离器,将滤波器系数提供给滤波器组,分离器生成与多个观测信号分离的多个分离信号 对应于分离矩阵。