Perceptual Objective Listening Quality Assessment (POLQA), The Third Generation ITU-T Standard for End-to-End Speech Quality Measurement Part I-Temporal Alignment

In this and the companion paper Part II, the authors present the Perceptual Objective Listening Quality Assessment (POLQA), the third-generation speech quality measurement algorithm, standardized by the International Telecommunication Union in 2011 as Recommendation P.863. In contrast to the previous standard (P.862 Perceptual Evaluation of Speech Quality), a more complex temporal alignment was developed allowing for the alignment of a wide variety of complex distortions for which P.862 was known to fail, such as multiple delay variations within utterances as well as temporal stretching and compression of the degraded signal. When this new algorithm is used in combination with the advanced perceptual model described in Part II, it provides a new measurement standard for predicting Mean Opinion Scores that outperforms the older PESQ standard, especially for wideband and super wideband speech signals (7 and 14 kHz audio bandwidth). Part I provides the basics of the POLQA approach and outlines the core elements of the temporal alignment.