Title :
Evaluation of objective measures applied on the noise suppressed speech signals with Chinese content
Author :
Huijun Ding;Jia Pan;Minmin Shen
Abstract :
Objective measures are favored and widely used by many researchers in evaluating the quality of noise-suppressed speech. A good and reliable objective measure should have property that it could evaluate speech quality in consistent and well correlated with subjective ratings. In this paper, several widely used objective measures are applied to the speech signals with the Chinese languages including Mandarin and Cantonese. The correlations between objective measure outputs and perceptual-subjective ratings are reported and analyzed. The experimental results show that the correlation with the language types of Mandarin and Cantonese are lower than the one with English and objective measures behave differently in Mandarin, Cantonese and English. Detail discussion and conclusion are presented as well.
Keywords :
"Speech","Speech enhancement","Correlation","Biomedical measurement","Noise","Noise measurement","Distortion measurement"
Conference_Titel :
Information and Automation, 2015 IEEE International Conference on
DOI :
10.1109/ICInfA.2015.7279412