集成多种自适应滤波算法的回声消除器

如何选择自适应算法的步长，从而有效解决收敛速度和稳态失调之间的矛盾是回声消除中的一个重要问题。论文提出一种集成多种自适应滤波算法的回声消除框架，以挖掘不同自适应滤波算法以及不同步长选择之间的互补性，来获得稳定的消除效果。所提算法可以分析同一时刻不同算法的误差，并始终选择一种最好的算法。通过对LMS、NLMS、PNLMS和IPNLMS这四种自适应算法的结合实验，显示了该算法可以集合各种算法以及步长选择的优点，具有更快的收敛速度和良好的稳态特性。

Echo Canceller Integrating Diverse Adaptive Filtering Algorithms

It is a significant problem how we select step-size of adaptive filtering algorithm so as to solve effectively me conflict between convergence speed and steady misalignment in echo cancellation. This paper presents a novel echo cancellation scheme which integrates a diverse set of adaptive filtering methods and different choices of step-size, such that their advantages can be integrated and the improved performance can be achieved. In the proposed scheme, the performance of different methods are analyzed, thus being able to keep selecting the best methods for output. An empirical study on the integration of four methods, namely, LMS, NLMS, PNLMS and IPNLMS, indicates that the proposed scheme is effective in terms of both convergence speed and good steadiness.