摘要
针对电话语音条件下的文本无关话者确认,提出了一种基于GMM(Gaussian mixturemodel)全统计参数和SVM(support vector machine)的话者确认方法,以克服语音特征参数直接建立SVM话者模型面临的困难.该方法使用由GM(general model)自适应均值得到的GMM提取统计参数,定义了一种合理利用全部统计参数的特征参数,并以此参数及线性核函数建立了具有良好性能的SVM话者模型.与GMM-UBM方法及另一种基于GMM统计参数和SVM的方法在NIST05SRE数据库中的实验比较,结果表明基于GMM全统计参数和SVM的话者确认方法拥有优异的性能.
An approach for text-independent speaker verification with telephone speech was proposed, based on GMM all statistical parameters and SVM to solve the problem of building SVM speaker models with speech features. By using GMM derived from the GM via adaptation of the means to extract statistical parameters, new parameters were defined based on all statistical parameters of SVM and were used with linear kernel to build SVM speaker models which had good performance. The experimental results of the approaches based on GMM-UBM and another GMM statistical parameters and SVM in the database of NIST05SRE show excellent properties of the proposed.
基金
国家自然科学基金(60272039)资助
关键词
高斯混合模型
统计特性参数
支持向量机
话者确认
Gaussian mixture model
statistical parameters
support vector machine
speaker verification
