首页 | 本学科首页   官方微博 | 高级检索  
     

基于听觉模型的客观音质评价方法研究
引用本文:吴淑珍,赵朝阳.基于听觉模型的客观音质评价方法研究[J].电子学报,1999,27(7):92-94.
作者姓名:吴淑珍  赵朝阳
作者单位:北京大学电子学系,北京,100871
摘    要:本文阐述了一种基于听觉模型的客观音质评价方法研究,我们在使用谱失真和谱包络失真进行了客观音质评价同时采用了听觉系统模拟的三个听觉感知模型,实验结果表明,在于听觉模型的谱夫真方法测量结果与主观评价更人一致性,在与主观评价具有同样相关系数时,采用听觉模型谱包失真方法的预测系数为4阶而LPC倒谱距离方法的预测系数为8阶。

关 键 词:客观音质评价  感知模型  谱失真测量  谱包络失真测量

A Study of Perceptually-Based Features for Objective Speech Quality Evaluation
Wu Shuzhen,Zhao Chaoyang.A Study of Perceptually-Based Features for Objective Speech Quality Evaluation[J].Acta Electronica Sinica,1999,27(7):92-94.
Authors:Wu Shuzhen  Zhao Chaoyang
Affiliation:Wu Shuzhen,Zhao Chaoyang; (
Abstract:This paper studies briefly measures for objective quality evaluation using perceptuallybased features.We used 3 sorts of perceptuallybased features for objective quality measures of spectral distortion and spectral envelop distortion.The experimental results show that the correspondence between spectral distortion measure of perceptuallybased features and the subjective quality evaluation (MOS) is better compared with general spectral distortion measure.The predeictive order of spectral envelop distortion used perceptuallybased features is reduced from 8 to 4,and the correlation coefficients between 2 objective measures and the subjective quality are the same.
Keywords:Objective speech quality evaluation  Perceptuallybased feature  Spectral distortion measure  Spectral envelop distortion measure  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号