An Objective Metric of Human Subjective Audio Quality Optimized for a Wide Range of Audio Fidelities

摘要

The goal of this paper is to develop an audio quality metric that can accurately quantify subjective quality over audio fidelities ranging from highly impaired to perceptually lossless. As one example of its utility, such a metric would allow scalable audio coding algorithms to be easily optimized over their entire operating ranges. We have found that the ITU-recommended objective quality metric, ITU-R BS.1387, does not accurately predict subjective audio quality over the wide range of fidelity levels of interest to us. In developing the desired universal metric, we use as a starting point the model output variables (MOVs) that make up BS.1387 as well as the energy equalization truncation threshold which has been found to be particularly useful for highly impaired audio. To combine these MOVs into a single quality measure that is both accurate and robust, we have developed a hybrid least-squares/minimax optimization procedure. Our test results show that the minimax-optimized metric is up to 36% lower in maximum absolute error compared to a similar metric designed using the conventional least-squares procedure.