机构地区: 中国科学技术大学信息科学技术学院多媒体计算与通信教育部—微软重点实验室
出 处: 《模式识别与人工智能》 2008年第1期28-33,共6页
摘 要: 提出一种结合统计模型与区分性模型优点的说话人确认方法:基于GMM多维概率输出的SVM话者模型的说话人确认.以目标说话人的GMM模型对一条语音的不同特征分量的概率输出作为特征参数,建立目标说话人的SVM模型.在NIST’05 8conv4w-lconv4w数据库上的实验表明该方法的有效性. In this paper, a text-independent speaker verification system based on GMM multidimensional likelihoods and SVM is proposed, which combines the advantages of both generative model and discriminative model. In this method, the GMM multidimensional likelihoods for the test speech are regarded as new features for SVM. Experiment results of text-independent speaker verification on NIST'05 8conv4w-1conv4w database show effectiveness of the proposed system.