自适应GMM聚类的SVM话者确认

SVM Speaker Verification Based on Adapted GMM-clustering Feature

支持向量机作为说话人建模方法用于与文本无关的话者确认研究时,如何提取适合SVM训练和测试的特征参数直接影响话者确认系统的性能和效率.根据高斯混合模型(GMM)聚类能力强的特点,提出一种基于自适应GMM聚类的说话人特征参数提取方法,通过自适应的GMM聚类将大样本、混叠严重的M FCC特征参数聚为小样本的、代表说话人个性特征的特征参数,并用于与文本无关的SVM话者确认.在N IST0′4 1side-1side数据库上的实验表明了该方法的有效性.

In text-independent speaker verification,how to extract typical feature which is suitable for the training and test of SVM greatly determines the performance of the SVM system.In this paper,a new SVM speaker verification method based on adapted GMM-clustering feature was proposed,in which adapted GMM was used to extract a small quantity of typical feature vectors from large numbers of speech data（MFCC） for its excellent scalability.Experiments on text-independent speaker verification in NIST′04 1side-1side data showed significant improvement compared to the baseline GMM-UBM system.