摘要
提出了一种对Ｉｔａｋｕｒａ 语音失真测度的改进方法——感知谱失真（ＰＳＤ） 测度方法，该方法通过模拟人的听觉特性把语音短时谱转变为符合听觉特性的感知谱，再以感知谱为基础，结合Ｉｔａｋｕｒａ 测度的优点来度量语音失真程度．通过对不同质量的语音信号进行仿真实验以及与Ｉｔａｋｕｒａ 测度方法作对比实验，结果表明ＰＳＤ测度克服了Ｉｔａｋｕｒａ 测度的不足，与语音质量的主观评价一致性较好，特别是在语音失真程度较大时ＰＳＤ测度明显优于Ｉｔａｋｕｒａ 测度．
To improve the Itakura speech distortion measure, a method, Perceptual Spectrum Distortion (PSD) measure, is proposed. In the PSD measure, the speech distortion distance is computed by simulating the auditory properties of human being and converting the short time speech spectrum to the perceptual speech spectrum. The results of preliminary simulation experiments show that the PSD measure is preferable and it is of better consistency with subjective assessment of speech quality.
出处
《华中理工大学学报》
CSCD
北大核心
1999年第10期101-103,共3页
Journal of Huazhong University of Science and Technology
基金
国防科工委资助
