What You Hear Is What You See: Audio Quality Metrics From Image Quality Metrics

TL;DR

This paper explores using image perceptual metrics, applied to spectrograms, to evaluate audio quality, leveraging similarities between auditory and visual neural processing, and customizes metrics for sound signals, showing promising correlation with human judgments.

Contribution

It introduces a novel approach of applying and customizing image quality metrics to assess audio signals via spectrograms, bridging visual and auditory perceptual models.

Findings

Spectrogram-based metrics correlate well with human audio quality ratings.

Customized metrics improve evaluation accuracy for sound signals.

Proposed method shows promise for objective audio quality assessment.

Abstract

In this study, we investigate the feasibility of utilizing state-of-the-art image perceptual metrics for evaluating audio signals by representing them as spectrograms. The encouraging outcome of the proposed approach is based on the similarity between the neural mechanisms in the auditory and visual pathways. Furthermore, we customise one of the metrics which has a psychoacoustically plausible architecture to account for the peculiarities of sound signals. We evaluate the effectiveness of our proposed metric and several baseline metrics using a music dataset, with promising results in terms of the correlation between the metrics and the perceived quality of audio as rated by human evaluators.