首页> 外国专利> Sound source localization method based CDR mask and localization apparatus using the method

Sound source localization method based CDR mask and localization apparatus using the method

机译:基于声源定位的基于CDR掩码的方法及使用该方法的定位装置

摘要

According to a first characteristic of the present invention, provided is a sound source localization method for achieving a technical problem of a mask based on a dispersion degree, which comprises the steps of: (a) receiving a signal mixed with a target sound source signal, a noise, and an echo signal through a multi-microphone including at least two microphones; (b) generating a binarization mask based on a dispersion degree using a ratio of consistency to dispersion degree (CDR) which is information on a target sound source and a noise source using the inputted signals; (c) preprocessing the input signal to the multi-microphone using the generated binarization mask; and (d) estimating a direction for a target sound source by performing a preset algorithm such as GCC-PHAT or SRP-PHAT on the preprocessed input signal.
机译:根据本发明的第一特征,提供了一种用于实现基于色散度的掩模的技术问题的声源定位方法,其包括以下步骤:(a)接收与目标声源信号混合的信号通过至少包括两个麦克风的多麦克风获得的噪声和回声信号; (b)使用所输入的信号,使用作为目标声源和噪声源的信息的一致性与分散度(CDR)之比,基于分散度生成二值化掩模; (c)使用生成的二值化掩模对输入到多麦克风的输入信号进行预处理; (d)通过对预处理的输入信号执行诸如GCC-PHAT或SRP-PHAT之类的预设算法来估计目标声源的方向。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号