College of Mathematics and Computer Science, Fuzhou University, China.
Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong.
Neural Netw. 2015 Jul;67:131-9. doi: 10.1016/j.neunet.2015.03.008. Epub 2015 Apr 7.
This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asymptomatically stable to the noise-constrained estimate. Because the noise-constrained estimate has a robust performance against non-Gaussian noise, the proposed recurrent neural network-based speech enhancement algorithm can minimize the estimation error of Kalman filter parameters in non-Gaussian noise. Furthermore, having a low-dimensional model feature, the proposed neural network-based speech enhancement algorithm has a much faster speed than two existing recurrent neural networks-based speech enhancement algorithms. Simulation results show that the proposed recurrent neural network-based speech enhancement algorithm can produce a good performance with fast computation and noise reduction.
本文提出了一种基于新的递归神经网络的卡尔曼滤波器的语音增强，基于噪声约束最小二乘估计。首先，通过使用所提出的递归神经网络对自回归过程建模的语音信号的参数进行估计，然后通过卡尔曼滤波恢复语音信号。所提出的递归神经网络对噪声约束估计是全局渐近稳定的。由于噪声约束估计对非高斯噪声具有鲁棒性能，因此基于所提出的递归神经网络的语音增强算法可以最小化卡尔曼滤波器参数在非高斯噪声下的估计误差。此外，由于具有低维模型特征，所提出的基于神经网络的语音增强算法的计算速度比现有的两种基于递归神经网络的语音增强算法快得多。仿真结果表明，所提出的基于递归神经网络的语音增强算法可以实现快速计算和降噪的良好性能。
