马静,侯丽敏,王朔中.基于全局背景模型和竞争者模型的说话人确认系统[J].声学技术,2007,(1):105~110 |
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 |
投稿时间:2005-07-01 修订日期:2005-11-01 |
DOI: |
中文关键词: 说话人确认 背景模型 竞争者模型 全局背景模型 |
英文关键词: speaker verification background speaker model cohort model universal background model |
基金项目: |
|
摘要点击次数: 1343 |
全文下载次数: 992 |
中文摘要: |
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。 |
英文摘要: |
Most comprehensive speaker verification systems use background speakers to model imposters.Based on analysis of general background speaker models,a new model combining the universal background model(UBM) with a cohort 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. |
查看全文
查看/发表评论 下载PDF阅读器 |
关闭 |
|
|
|