在此提出一种利用线性预测误差去除语音中的加性白噪声的方法。
It presents a new method on reducing additive white noise in speech signal using linear prediction error.
对多信道模型的输出应用线性预测，证明了预测误差只包含多信道模型冲激响应在第一个时隙的参数，并给出最佳线性预测器的长度。
A linear prediction approach is applied to the output of this SIMO model and we prove that the prediction error contains the parameters of the first time slot of the model impulse response.
研究证明，小波神经网络所建立的非线性误差校正模型有较好的预测效果，能够有效地预测非线性经济系统。
The results validate more validity of nonlinear error correction model on the wavelet neural network than linear vector autoregressive model, and forecast validly the nonlinear economy system.
预测滤波器是一种基于非线性系统模型的滤波方法，它通过使输出一步前向预测误差最小来估计模型误差，具有较高的估计精度。
The Predictive Filter is an estimation method based on nonlinear system model, which determines the optimal model error using a one-step ahead control approach to provide accurate state estimations.
模拟的结果显示ANN模型比线性回归模型有更好的预测能力，预测的平均相对误差：ANN模型为14.9%，线性回归模型为25.8%。
Simulation results showed that the ANN model gave better predictions than the regressive model. The average relative error of ANN was 14.9% and that of linear regression was 25.8%.
本文先介绍了用最小二乘法进行线性回归预测的方法，并分析了其不足，即当存在着极端的异常情况时，往往存在着较大的预测误差。
In first the linear regression model resulted from least square method is presented and its disadvantage is analyse, great forecasting error exists when extreme abnormal case exists.
该模型利用RBF神经网络的非线性逼近能力对预测日负荷进行了预测，并采用在线自调整因子的模糊控制对预测误差进行在线智能修正。
The model forecasts the daily load by the nonlinear approaching capacity of the RBF neural network, than corrects the errors by on-line self-tuning factors of fuzzy control.
结果显示，该模型预测效果明显优于传统的线性自回归预测模型，各月平均的平均绝对误差（MAE）和均方误差（RMSE）达到41.8和55.7。
Results show that the RBFNN is obviously superior to the traditional linear model, and its MAE (mean absolute error) and RMSE (root mean square error) are 41.8 and 55.7, respectively.
模型预测值与国标法测定的酸值高度线性相关，盲样验证相对误差均小于10%。
The linear correlativity of the determination of the acid value between two methods was very well, the relative deviation of blind samples experiment's data were less than 10%.
模型预测值与国标法测定的酸值高度线性相关，盲样验证相对误差均小于10%。
The linear correlativity of the determination of the acid value between two methods was very well, the relative deviation of blind samples experiment's data were less than 10%.
应用推荐