Abstract
The Kalman filter is widely used for addressing acoustic echo cancellation (AEC) problems due to their robustness to double-talk and fast convergence. However, the inability to model nonlinearity and the need to tune control parameters cast limitations on such adaptive filtering algorithms. In this paper, we integrate the frequency domain Kalman filter (FDKF) and deep neural networks (DNNs) into a hybrid method, called KalmanNet, to leverage the advantages of deep learning and adaptive filtering algorithms. Specifically, we employ a DNN to estimate nonlinearly distorted far-end signals, a transition factor, and the nonlinear transition function in the state equation of the FDKF algorithm. Experimental results show that the proposed KalmanNet improves the performance of FDKF significantly and outperforms strong baseline methods.
Abstract (translated)
卡尔曼滤波器被广泛用于解决声学回声消除(AEC)问题,因为它们对多嘴和快速收敛的鲁棒性。然而,无法建模非线性和需要调整控制参数的限制对这些自适应滤波算法形成了限制。在本文中,我们将频率域卡尔曼滤波器(FDKF)和深度神经网络(DNN)集成到一个混合方法中,称为卡尔曼Net,以利用深度学习和自适应滤波算法的优势。具体来说,我们使用DNN来估计非线性失真的远端信号、过渡因子和FDKF算法状态方程中的非线性过渡函数。实验结果显示, proposed KalmanNet significantly improves the performance ofFDKF算法,并比强大的基线方法表现更好。
URL
https://arxiv.org/abs/2301.12363
