PESQ测量语音增强算法性能不确定性的研究  

Uncertainty Evaluation of Objective Speech Quality Measurement Using in Speech Enhancement Algorithms

作　　者：周璐[1] 邱小军[1] 林志斌[1] 

机构地区：[1]近代声学教育部重点实验室南京大学声学研究所,江苏南京210093

出　　处：《电声技术》2010年第1期71-73,85,共4页Audio Engineering

基　　金：国家自然科学基金(10674068)

摘　　要：对用感知语音质量评价标准(PESQ)测量语音增强算法性能的不确定性进行了研究,给出了不同测试条件下,语音增强算法所得PESQ值的不确定性。通过对结果的分析,比较了轿车噪声条件下几种语音增强算法的性能,并对结果进行了可靠性分析。The measurement uncertainty of speech enhancement performance using perceptual speech quality evaluation criteria PESQ（Perceptual Evaluation of Speech Quality） is studied. The uncertainty of the PESQ results under different test conditions is summarized. Through the analysis of the results, the performance of several speech enhancement algorithms under the ear noise conditions is compared, and the reliability of the results is discussed.

关 键 词：PESQ 语音增强 不确定性 

分 类 号：TN912[电子电信—通信与信息系统]