Hammerstein model-based nonlinear echo cancelation using a cascade of neural network and adaptive linear filter

机译：神经网络和自适应线性滤波器级联的基于Hammerstein模型的非线性回声消除

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We present a novel nonlinear echo cancellation method that assumes the Hammerstein nonlinear system model. Model parameters are identified using a neural network followed by an adaptive linear filter. The parameters of both subsystems are estimated separately, which allows the utilization of computationally efficient conventional methods. The proposed method is verified on simulated as well as on real-world signals. In comparison to power-filter echo cancelers, the method achieves significantly higher echo suppression provided that the excitation signal is white noise, and it yields comparable performance when the signal is speech.

机译：我们提出了一种新的非线性回声消除方法，该方法假设了Hammerstein非线性系统模型。使用神经网络和自适应线性滤波器来识别模型参数。两个子系统的参数分别估算，从而可以利用计算效率高的常规方法。所提出的方法已在仿真信号和实际信号上得到验证。与电源滤波器的回声消除器相比，如果激励信号为白噪声，则该方法可实现更高的回声抑制，并且当信号为语音时，它可产生可比的性能。

著录项

来源
《2016 IEEE International Workshop on Acoustic Signal Enhancement》|2016年|1-5|共5页
会议地点 Xian(CH)
作者
Jiri Malek; Zbyněk Koldovský;
展开▼
作者单位

Faculty of Mechatronics, Informatics, and Interdisciplinary Studies, Technical University of Liberec, Studentská 2, 461 17 Liberec, Czech Republic;

Faculty of Mechatronics, Informatics, and Interdisciplinary Studies, Technical University of Liberec, Studentská 2, 461 17 Liberec, Czech Republic;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Speech; Neural networks; Adaptation models; Computational modeling; Nonlinear distortion; Echo cancellers;

机译：语音;神经网络;适应模型;计算模型;非线性失真;回声消除器;

相似文献

外文文献
中文文献
专利

1. An adaptive for filter for echo cancelling using least squares with nonlinear optimal input design [J] . Z.Dj.Banjac, B.D.Kovacevic, M.M.Milosavljevic Control and Intelligent Systems . 2002,第1期

机译：非线性最小输入设计的自适应滤波器，用于最小二乘消除回声
2. A Neural Network-Based Nonlinear Acoustic Echo Canceller [J] . Halimeh Mhd Modar, Huemmer Christian, Kellermann Walter IEEE signal processing letters . 2019,第12期

机译：基于神经网络的非线性回声消除器
3. Linearized Adaptive Filter for a Nonlinear System Using Neural Network Based on the Extended Kalman Filter [J] . Hiroshi Kinjo, Shiro Tamaki, Tetsuhiko Yamamoto 電気学会論文誌. C . 1997,第3期

机译：基于扩展卡尔曼滤波器的神经网络非线性系统的线性自适应滤波器
4. Hammerstein model-based nonlinear echo cancelation using a cascade of neural network and adaptive linear filter [C] . Jiri Malek, Zbyněk Koldovsky IEEE International Workshop on Acoustic Signal Enhancement . 2016

机译：基于Hammerstein模型的非线性回声消除，使用级联神经网络和自适应线性滤波器
5. Comparison of adaptive filter and neural network approaches to canceling current harmonics. [D] . Warner, Douglas Edward. 2000

机译：自适应滤波器和神经网络消除电流谐波方法的比较。
6. Approximate nonlinear filtering with a recurrent neural network [O] . Anna Kutschireiter, Simone C Surace, Henning Sprekeler, 2015

机译：递归神经网络的近似非线性滤波
7. Linearized Adaptive Filter for a Nonlinear System Using Neural Network Based on the Extended Kalman Filter [O] . Hiroshi Kinjo, Shiro Tamaki, Tetsuhiko Yamamoto 1997

机译：基于扩展卡尔曼滤波器的神经网络的非线性系统线性化自适应滤波器

Hammerstein model-based nonlinear echo cancelation using a cascade of neural network and adaptive linear filter

摘要

著录项

相似文献

相关主题

期刊订阅