基于全局背景模型和竞争者模型的说话人确认系统

Speaker verification based on UBM and cohort model

大多数说话人确认系统都设置一个背景模型用于描述假冒者的特性。文章提出一种新的说话人确认的背景模型,对所有说话人采用同一全局背景模型(简称UBM),并为每个说话人建立一个竞争者模型(cohort model)。在全局背景模型不能做出准确判断的情况下,启用竞争者模型再次进行判决。该模型充分利用了传统全局背景模型和竞争者模型的互补性。实验表明新的背景模型使系统性能有较明显的提高。

Most comprehensive speaker verification imposters. Based on analysis of general background universal background model （UBM） with a cohort systems use background speakers to model speaker models, a new model combining the model is proposed. In the proposed speaker verification system, the same UBM is set for all claimed speaker, and a cohort model is set for each speaker. When the UBM fails to give a definite decision, the cohort model is used to make a verdict. The new background speaker model takes advantages of both UBM and the cohort model. Experimental results show that an equal error rate lower than conventional techniques is obtainable.