首页> 外文会议>2016 IEEE International Workshop on Acoustic Signal Enhancement >Constrained multi-channel linear prediction for adaptive speech dereverberation
【24h】

Constrained multi-channel linear prediction for adaptive speech dereverberation

机译:约束多通道线性预测的自适应语音去混响

获取原文
获取原文并翻译 | 示例

摘要

This paper presents a speech dereverberation algorithm combining adaptive multi-channel linear prediction (MCLP) with a statistical model for the undesired reverberation. More specifically, we propose to constrain the power of the MCLP-based late reverberation estimate with the late reverberant power estimated using the exponential decay model, thereby preventing excessive cancellation of the speech signal. Simulation results show that incorporating the constraint improves the performance of the adaptive dereverberation method when the prediction filters need to adapt quickly.
机译:本文提出了一种语音去混响算法,该算法将自适应多通道线性预测(MCLP)与统计模型相结合,用于不需要的混响。更具体地,我们提出将基于MCLP的后期混响估计的功率与使用指数衰减模型估计的后期混响功率进行约束,从而防止语音信号的过度抵消。仿真结果表明,当预测滤波器需要快速适应时,加入约束可以提高自适应去混响方法的性能。

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