机构地区: 深圳大学
出 处: 《计算机工程》 2009年第16期4-6,共3页
摘 要: 在基于支持向量机(SVM)的文本无关的说话人确认中,为提高SVM话者模型的训练效率和区分性能,提出2种基于高斯混合模型(GMM)的冒认话者选取方法——通过GMM概率评分,为每个目标说话人选取最接近的话者作为冒认话者用于SVM话者模型的训练,不仅提高模型的训练效率,而且提高SVM模型的区分性,有效地改进系统性能。在NIST’04 1side-1side数据库上的实验表明该方法的有效性。 In text-independent Support Vector Machine(SVM) speaker verification, impostor selection for SVM training directly determines its efficiency and performance. This paper proposes two Gaussian Mixture Model(GMM)-based methods for impostor selection. By GMM likelihoods, the most similar impostors to the target speaker are selected for SVM training, which makes the target speaker models more discriminative. Experiments on text-independent SVM speaker verification in NIST'04 1 side-1 side data show significant improvement.