【24h】

FDM array based dual channel speech enhancement method

机译:基于FDM阵列的双通道语音增强方法

获取原文

摘要

With more and more miniature speech communication devices coming out,two-element microphone array draws a lot of attention due to its simplicity and the ability to suppress directional noise.This paper develops a dual channel speech enhancement method by combining the first-order differential microphone (FDM) array and the single-channel spectral enhancement techniques.The method can obtain an estimate of speech signal and noise signal simultaneously,and it corrects the noise spectrum in a real-time manner.Compared with the existing dual channel speech enhancement techniques,the proposed method can achieve 2~6 dB output signal-to-noise ratio (SNR) gain with only 1/3 computational complexity.
机译:随着越来越多的小型语音通信设备的出现,二元麦克风阵列由于其简单性和抑制定向噪声的能力而引起了人们的广泛关注。本文通过结合一阶差分麦克风,开发了一种双通道语音增强方法。 (FDM)阵列和单通道频谱增强技术。该方法可以同时获得语音信号和噪声信号的估计,并实时校正噪声频谱。与现有的双通道语音增强技术相比,该方法可以实现2〜6 dB的输出信噪比(SNR)增益,计算复杂度仅为1/3。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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