P.563—The ITU-T Standard for Single-Ended Speech Quality Assessment 论文

2006IEEE Transactions on Audio Speech and Language Processing引用 223
Speech and Audio ProcessingAdvanced Adaptive Filtering TechniquesSpeech Recognition and Synthesis

摘要

Objective voice quality assessment has been the subject of research for many years. Up until very recently, objective models required a copy of the unprocessed signal for estimating the quality of a signal transmitted across a telecommunication network, making live call monitoring impossible. This paper introduces a method for nonintrusive assessment of speech quality for narrow-band telephony, which was approved by the International Telecommunication Union (ITU-T) in May 2004. Essentially based on models of voice production and perception, the algorithm demonstrates good performance on more than 48 subjective experiments representing most distortions that occur on voice networks