基于PCS-PCA分类器和支持向量机的说话人确认

针对语音识别率不高的问题,提出一种基于PCS-PCA和支持向量机的分级说话人确认方法.首先采用主成分分析法对话者特征向量降维的同时,得到说话人特征向量的主成份空间,在此空间中构造PCS-PCA分类器,筛选可能的目标说话人,然后采用支持向量机进行最终的说话人确认.仿真实验结果表明该方法具有较高的识别率和较快的训练速度.

Hierarchical speaker verification based on TES-PCA classifier and support vector machine

A novel hierarchical speaker verification approach based on PCS-PCA classifier and support vector machine was proposed in this paper. Firstly, PCA was utilized to reduce the dimension of registered speakers＇s feature vectors, simultaneously principal component space was obtained based on the transform matrix. The possible target speakers were selected fleetly by PCS-PCA classifier. And then, the target speaker was found using support vector machine. The experiment results showed that our method has hidaer recognition accuracv and faster training soeed.