一种新的用于语音主观质量评价的谱失真参数
A NEW PARAMETER OF SPECTRAL DISTORTION FOR PREDICTING SUBJECTIVE QUALITY OF SPEECH
-
摘要: 该文分析和讨论了各种语音主观质量评价的客观方法,提出了一种考虑了人耳的屏蔽效应,且正比于人耳听觉的Bark域谱失真参数PBSD(Perception-based Bark Spectral Distortion),用来映射语音的主观MOS分值。实验表明,基于该参数及其主客观映射关系,所得到的各类语音编译码系统的主观MOS预测分,平均和最大预测偏差均较小。论文最后利用PBSD参数代替MSE参数,设计的语音编码系统,改善了解码语音的主观听觉质量。
-
关键词:
- 语音信号; MOS分; 预测
Abstract: This paper analyses various objective measures for the prediction of subjective quality of speech. A new Perception-based Bark Spectral Distortion (PBSD) parameter is pre- sented, which takes the masking property of human ear into consideration, to predict Mean Opinion Score(MOS) of speech quality. Experiments prove that this map from objective mea-sure to subjective MOS based on the calculation of PBSD has rather small prediction error. The PBSD parameter is applied to designing new speech codec in place of MSE parameter and the subjective quality of decoded speeches is improved. -
S.R. Quackenbush, T. P. Barnwell, M. A. Clements, Objective Measures of Speech Quality, New York, U.S.A., Prentice Hall, 1988, 第 2 章. ［2］丁瑾,钟涛,胡健栋,语音质量的一种新的评价方法,电子学报,1997,25(4),6-9.[2]Shihua Wang, A. Sekey, A. Gersho, An objective measure for predicting subjective quality of speech coders, IEEE Journal on Selectted Areas in Communications, 1992, 10(5), 829-829.[3]M.M. Meky.[J].Tarek, N, Saadawi, A perceptually-based objective measure for speech coders using abductive network, ICASSP96, Atlanta, U.S.A.1996,:-[4]Nobuhiko Kitawaki.[J].et al, Artificial voice signal for objective quality evaluation of speech coding system, ICC89, Boston, MA, U.Y.A.1989,:-[5]J.D. Johnston, Transform coding of audio signals using perceptual noise, IEEE on Selected Areas in Communications, 1988, 6(2), 314-323.[6]L.E. Kinsler et al, Fundamental of Acoustics, New York, U.S.A.,,John Wiley Sons Inc., 1982, third edition, 246-278.[7]T W Parsons著,文成义等译,语音处理,西安电子科技大学情报资料室,1989,3,49-114. -
计量
- 文章访问数: 2185
- HTML全文浏览量: 113
- PDF下载量: 963
- 被引次数: 0
下载:
