# Perceptual Musical Features for Interpretable Audio Tagging Source: [Perceptual Musical Features for Interpretable Audio Tagging]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:22:12.513Z Authors: Vassilis Lyberatos, Spyridon Kantarelis, Edmund Dervakos, Giorgos Stamou Published: 2023-12-18T14:31:58.000Z ## Abstract In the age of music streaming platforms, the task of automatically tagging music audio has garnered significant attention, driving researchers to devise methods aimed at enhancing performance metrics on standard datasets. Most recent approaches rely on deep neural networks, which, despite their impressive performance, possess opacity, making it challenging to elucidate their output for a given input. While the issue of interpretability has been emphasized in other fields like medicine, it has not received attention in music-related tasks. In this study, we explored the relevance of interpretability in the context of automatic music tagging. We constructed a workflow that incorporates three different information extraction techniques: a) leveraging symbolic knowledge, b) utilizing auxiliary deep neural networks, and c) employing signal processing to extract perceptual features from audio files. These features were subsequently used to train an interpretable machine-learning model for tag prediction. We conducted experiments on two datasets, namely the MTG-Jamendo dataset and the GTZAN dataset. Our method surpassed the performance of baseline models in both tasks and, in certain instances, demonstrated competitiveness with the current state-of-the-art. We conclude that there are use cases where the deterioration in performance is outweighed by the value of interpretability. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-class Music Classification on Music4All](): Multi-class Music Classification; Music4All; Accuracy: 48.59. - [Multi-class Music Classification on AudioSet](): Multi-class Music Classification; AudioSet; Accuracy: 50. - [Music Mood Tagging on MTG-Jamendo (test subset)](): Music mood/theme tagging; MTG-Jamendo mood theme subset (test); AUC: 0.727. - [Genre Tagging on GTZAN 1.0 (test)](): Genre tagging; GTZAN 1.0 (test); Accuracy: 76.5. - [Multi-label Music Auto-tagging on MTG-Jamendo](): Multi-label Music Auto-tagging; MTG-Jamendo; ROC-AUC: 74.64. ## Original sources and implementation [Original paper]() [PDF]()