MLP语音信号非线性预测器

讨论了MLP（Multi-Layer Perceptron)语音信号非线性预测器的实现。为了使MLP能够适用于语音信号预测，对MLP的误差准则进行了修正以减轻神经网络模型与语音模型之间的过匹配。为了提高MLP的训练速度，提出了一种线性化逐层优化（LOLL）MLP训练算法。实验结果显示该非线性预测器的预测信噪比约比线性预测器提高2dB，而且它还可以同时完成长时预测器的功能；误差准则修正使非线性预测器的预测信噪比提高了0.35dB。

Speech Nonlinear Predictor with Multi-Layer Perceptron

A speech nonlinear predictor with Multi-Layer Perceptron (MLP) is demonstrated in this paper. Compared with existing nonlinear speech predictors, two innovations are embodied in the predictor. One is the modification of mean square error function where weight regularization is used to ease overfitting. The other is the Linearized Optimization Layer by Layer (LOLL) algorithm which speeds up MLP's training procedure. Experimental results show us that: the prediction SNR of the proposed nonlinear predictor is about 2 dB higher than that of linear one at the same prediction order. A speech nonlinear predictor can practice both short term prediction and long-term prediction at the same time. Weight regularization adds 0.35 dB to prediction SNR.