首页> 外国专利> SIGNAL SEPARATION SYSTEM AND METHOD FOR SELECTING THRESHOLD TO SEPARATE SOUND SOURCE

SIGNAL SEPARATION SYSTEM AND METHOD FOR SELECTING THRESHOLD TO SEPARATE SOUND SOURCE

机译:选择阈值以分离声音源的信号分离系统和方法

摘要

A signal separation system and method for automatically selecting a threshold value for sound source separation is disclosed. A signal separation system calculates two power sequences for each of a target signal and a disturbance signal using a target mask and a complementary mask for a signal received from a plurality of microphones and outputs a nonlinearity to the two power sequences A threshold value for noise masking is set so that the calculated correlation coefficient has a minimum value.
机译:公开了一种用于自动选择用于声源分离的阈值的信号分离系统和方法。信号分离系统针对从多个麦克风接收到的信号使用目标掩模和互补掩模为目标信号和干扰信号中的每一个计算两个功率序列,并将非线性度输出到两个功率序列用于噪声掩蔽的阈值设定为使得计算出的相关系数具有最小值。

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