In this paper, a speaker identification system is proposed based on classify Fea-ture Sub-space Gaussian Mixture Model and Neural Net fusion (FS-GMM/NN) .

• 该文提出了一种基于分类高斯混合模型和神经网络融合(FS-GMM/NN)的说话人识别方法，通过对特征矢量进行聚类分析，将说话人的训练语音分成若干类。