A Data-driven Cognitive Salience Model for Objective Perceptual Audio Quality Assessment

TL;DR

This paper introduces a novel data-driven cognitive salience model that enhances objective perceptual audio quality assessment by explicitly modeling the interaction between cognitive effects and degradation metrics, leading to improved prediction accuracy.

Contribution

The paper proposes a new salience model that incorporates cognitive effects into the quality mapping process, improving performance with limited training data.

Findings

The salience model outperforms traditional statistical learning systems.

Incorporating cognitive effects improves prediction accuracy.

The approach is validated on a representative dataset.

Abstract

Objective audio quality measurement systems often use perceptual models to predict the subjective quality scores of processed signals, as reported in listening tests. Most systems map different metrics of perceived degradation into a single quality score predicting subjective quality. This requires a quality mapping stage that is informed by real listening test data using statistical learning (i.e., a data-driven approach) with distortion metrics as input features. However, the amount of reliable training data is limited in practice, and usually not sufficient for a comprehensive training of large learning models. Models of cognitive effects in objective systems can, however, improve the learning model. Specifically, considering the salience of certain distortion types, they provide additional features to the mapping stage that improve the learning process, especially for limited amounts of training data. We propose a novel data-driven salience model that informs the quality mapping stage by explicitly estimating the cognitive/degradation metric interactions using a salience measure. Systems incorporating the novel salience model are shown to outperform equivalent systems that only use statistical learning to combine cognitive and degradation metrics, as well as other well-known measurement systems, for a representative validation dataset.