The Kalman filter has been adopted in acoustic echo cancellation due to its robustness to double-talk, fast convergence, and good steady-state performance. The performance of Kalman filter is closely related to the estimation accuracy of the state noise covariance and the observation noise covariance. The estimation error may lead to unacceptable results, especially when the echo path suffers abrupt changes, the tracking performance of the Kalman filter could be degraded significantly. In this paper, we propose the neural Kalman filtering (NKF), which uses neural networks to implicitly model the covariance of the state noise and observation noise and to output the Kalman gain in real-time. Experimental results on both synthetic test sets and real-recorded test sets show that, the proposed NKF has superior convergence and re-convergence performance while ensuring low near-end speech degradation comparing with the state-of-the-art model-based methods. Moreover, the model size of the proposed NKF is merely 5.3 K and the RTF is as low as 0.09, which indicates that it can be deployed in low-resource platforms.

翻译：Kalman 过滤器已被的声音回声取消, 原因是它具有双轨、 快速趋同和良好稳定状态性能。 Kalman 过滤器的性能与状态噪音共变和观测噪音共变的估计准确性密切相关。 估计错误可能导致无法接受的结果, 特别是当回声路径发生突变时, Kalman 过滤器的跟踪性能可能显著退化。 在本文中, 我们提议神经卡尔曼过滤器( NKF ), 它使用神经网络隐含地模拟状态噪音和观测噪音的共变, 并实时输出Kalman的增益。 合成测试器和实时记录测试器的实验结果显示, 拟议的NKF 具有高度的趋同和再相近端声音的性能, 同时确保与基于状态的模型的方法相比, 低端的语音退化。 此外, 拟议的 NKF 的模型大小只有5.3 K, 而 RTF 和 0.09 一样低, 这表明它可以部署在低资源平台上。