【摘要】 针对现有说话人识别系统识别率不高,鲁棒性能差的缺点,提出了一种基于超向量的核函数构造方法。通过对超向量进行KL散度变换和L2线性内积变换,分别得到KL散度线性核函数、KL散度非线性核函数以及L2内积核函数。实验结果表明,将这三种核函数分别应用于支持向量机的说话人识别系统,可以得到优于常规核函数的识别性能。更多还原

【Abstract】 In order to improve the recognition ratio and weak robustness of speaker recognition system,a new SVM-classifier based on supervector kernel function is proposed in this paper.These new kernels,KL divergence linear kernel function,KL nonlinear ker-nel function and L2 inner product kernel function based on supervetor,are generated.Then these new kernel functions are applied in-to speaker recognition system and good experiment results are achieved.更多还原