When LPC vocoder exactly extracts vocal tract parameters, whether an excitation model is good of not will severoly affect the quality of the synthetic speech.
LPC 声码器在准确提取声道参数的情况下，激励模型的优劣直接影响着综合语音的质量。
This software works by analysing 117 parameters of an individual's voice to build up a profile of his vocal tract.
这个软件通过分析个体声音的117种参数，为用户建立特定的声音档案。
The vocal-tract mapping algorithm is the key part, so formant parameters which are estimated by the root-finding method based on LP analysis, are chosen for the transformation parameters.
其中，声道参数的转换是获得高质量重建语音的关键，所以选择声道共振峰参数作为待转换的特征参数，利用线性预测求根法提取共振峰参数。
应用推荐