针对支持向量机不能直接处理动态时间序列的语音数据问题,提出一种基于PCS-PCA分类器和AOI-Fisher分值(add original information fisher score)法的序列特征提取方法.首先利用PCA对每位注册说话人的特征向量进行维数约简,由转换矩阵得...针对支持向量机不能直接处理动态时间序列的语音数据问题,提出一种基于PCS-PCA分类器和AOI-Fisher分值(add original information fisher score)法的序列特征提取方法.首先利用PCA对每位注册说话人的特征向量进行维数约简,由转换矩阵得到每位说话人的主成分空间(principal component space,PCS),在此空间上快速判断出可能的R个说话人;然后在R个可能说话人的约简向量集上建立高斯混合模型;最后利用AOI-Fisher分值法进行向量定长转换的同时,为每位说话人的特征向量添加一维原始分类信息logP(X|θ).仿真实验结果表明,将该序列特征提取方法应用于SVM说话人确认系统,在不影响系统识别速度的情况下,具有较高的识别性能.展开更多
We are concerned with the maximization of tr（V T AV）/tr（V T BV）＋tr（V T CV） over the Stiefel manifold {V ∈ R m×l ｜ V T V = Il} （l 〈 m）, where B is a given symmetric and positive definite matrix, A and...We are concerned with the maximization of tr（V T AV）/tr（V T BV）＋tr（V T CV） over the Stiefel manifold {V ∈ R m×l ｜ V T V = Il} （l 〈 m）, where B is a given symmetric and positive definite matrix, A and C are symmetric matrices, and tr（. ） is the trace of a square matrix. This is a subspace version of the maximization problem studied in Zhang （2013）, which arises from real-world applications in, for example, the downlink of a multi-user MIMO system and the sparse Fisher discriminant analysis in pattern recognition. We establish necessary conditions for both the local and global maximizers and connect the problem with a nonlinear extreme eigenvalue problem. The necessary condition for the global maximizers offers deep insights into the problem, on the one hand, and, on the other hand, naturally leads to a self-consistent-field （SCF） iteration to be presented and analyzed in detail in Part II of this paper.展开更多
文摘针对支持向量机不能直接处理动态时间序列的语音数据问题,提出一种基于PCS-PCA分类器和AOI-Fisher分值(add original information fisher score)法的序列特征提取方法.首先利用PCA对每位注册说话人的特征向量进行维数约简,由转换矩阵得到每位说话人的主成分空间(principal component space,PCS),在此空间上快速判断出可能的R个说话人;然后在R个可能说话人的约简向量集上建立高斯混合模型;最后利用AOI-Fisher分值法进行向量定长转换的同时,为每位说话人的特征向量添加一维原始分类信息logP(X|θ).仿真实验结果表明,将该序列特征提取方法应用于SVM说话人确认系统,在不影响系统识别速度的情况下,具有较高的识别性能.
基金supported by National Natural Science Foundation of China(Grant Nos.11101257 and 11371102)the Basic Academic Discipline Program+3 种基金the 11th Five Year Plan of 211 Project for Shanghai University of Finance and Economicsa visiting scholar at the Department of Mathematics,University of Texas at Arlington from February 2013 toJanuary 2014supported by National Science Foundation of USA(Grant Nos.1115834and 1317330)a Research Gift Grant from Intel Corporation
文摘We are concerned with the maximization of tr（V T AV）/tr（V T BV）＋tr（V T CV） over the Stiefel manifold {V ∈ R m×l ｜ V T V = Il} （l 〈 m）, where B is a given symmetric and positive definite matrix, A and C are symmetric matrices, and tr（. ） is the trace of a square matrix. This is a subspace version of the maximization problem studied in Zhang （2013）, which arises from real-world applications in, for example, the downlink of a multi-user MIMO system and the sparse Fisher discriminant analysis in pattern recognition. We establish necessary conditions for both the local and global maximizers and connect the problem with a nonlinear extreme eigenvalue problem. The necessary condition for the global maximizers offers deep insights into the problem, on the one hand, and, on the other hand, naturally leads to a self-consistent-field （SCF） iteration to be presented and analyzed in detail in Part II of this paper.
