additive class

A classified linearly weighted transformation based on a radial basis function neural network was presented to reduce transformation error caused by inaccurate classification of classified.

为了克服分类线性转换算法(CLT)中分类不准带来的误差,引入了分类线性加权转换的策略,给出了一种基于径向基函数神经网络的分类线性加权转换算法(WCLT)。

Voice conversion from source speaker to target speaker based on classified linearly weighted transformation;

为了克服一般分类线性转换算法中分类不准确所带来的误差,本文引入了分类线性加权转换的策略,根据不同子类的转换函数对谱特性的贡献,赋予不同的加权系数,给出了一种基于GMM后验概率加权的线性转换算法。