NLMS算法是回声消除器中最常用的算法之一，然而语音信号的强相关性使NLMS(归一化最小均方)算法的收敛速度变慢。
NLMS (normalized least mean square) algorithm is widely used in echo canceller. However, due to high correlation of speech signals, the performance of echo canceller based on NLMS is depressed.
正是这种正反馈的交易机制，自我增强了预期归一化的速度与程度，导致流动性黑洞的出现。
It is the positive feedback trading and self-reinforcing mechanism, which enforced the expectations normalized speed and degree. So the liquidity black hole appears.
针对施工数据，根据数据归一化的原则，确定了一个比较合理的归一化方法，提高了网络学习的效率和网络收敛的速度。
A reasonable normalization method is made certain by the normalization principle and the data of construction. This method increases the learning efficiency and the rate of convergence of the network.
应用推荐